[R] sample weights in ols
Hello all, I am wondering if there is a way to specify sampling weights for an ols model using sample weights. For instance, right now, my code is: fit.ex<-lm(y~x1+x2+x3+...xk,data=dataset,weights=weightvariable.) summary(fit.ex) But, there is almost no difference in the coefficients nor standard errors. I am skeptical that I am using the option correctly since many posts state that the "weights" option is for weighted least squares. Or is this the same thing? Any help is appreciated! Thanks Carlos -- View this message in context: http://r.789695.n4.nabble.com/sample-weights-in-ols-tp3510865p3510865.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Setting NA to blank
Hi > Re: [R] Setting NA to blank > > I asked because I thought it'd solve an issue I had. I was actually being > quite rash in asking this question and for that, I apologize. > > I wanted to know because I was attempting to create a heatmap where the NA > values would not be shown while all the outputs with actual numerical value > will be shown. I had assumed that setting the NA's to blanks would fix the > issue, but it hadn't. I refrained from immediately asking another question > so I that I can look further into this. If you used heatmap function from stats package I believe that NA values are not displayed so they appear as white. So basically you should not need any change. It is usually better then assume what you think the functions are doing to learn what they actually do by consulting help page. You could also try examples provided at bottom of almost each help page and modify it to suit your needs. Regards Petr > > I hope that answers your question. > > On Mon, May 9, 2011 at 4:21 PM, Ted Harding wrote: > > > John Kane's reply sums it up! (Though you could use "", > > instead of " ", which would give you an "empty string" > > instead of the "space" character; but the resulting > > matrix would still consist entirely of "character" > > elements). > > > > However, the real reason I am following up is to ask > > why you want the blank instead of the NA. > > > > If it is just for printing out or display, then the > > fact that the matrix has been converted to character > > probably does not matter. > > > > But if it is for compatibility with some other > > computational software that (e.g.) expects missing > > values to be represented by a blank, or some "null" > > representation, then it may not be so straightforward. > > > > So, if that might be an issue, please describe for us > > how you intend to use the result. > > > > Ted. > > > > On 09-May-11 19:56:39, Dat Mai wrote: > > > Thank you kind sir! > > > > > > On Mon, May 9, 2011 at 3:25 PM, John Kane wrote: > > > > > >> > > >> (mat <- matrix(c(1,2,3,NA),2)) > > >> mat[is.na(mat)] <- " " > > >> mat > > >> > > >> But if you have a numerical matrix it coverts the matrix to character. > > >> > > >> --- On Mon, 5/9/11, Dat Mai wrote: > > >> > > >> > From: Dat Mai > > >> > Subject: [R] Setting NA to blank > > >> > To: r-help@r-project.org > > >> > Received: Monday, May 9, 2011, 2:46 PM > > >> > Hey All, > > >> > > > >> > I have a matrix m, and I wish to set all the NA values to > > >> > blank. How would I > > >> > do so? > > >> > > > >> > -- > > >> > Best, > > >> > Dat Mai > > >> > PhD Rotation Student > > >> > Albert Einstein College of Medicine > > > > > > E-Mail: (Ted Harding) > > Fax-to-email: +44 (0)870 094 0861 > > Date: 09-May-11 Time: 21:21:07 > > -- XFMail -- > > > > > > -- > Best, > Dat Mai > PhD Rotation Student > Albert Einstein College of Medicine > >[[alternative HTML version deleted]] > > __ > R-help@r-project.org mailing list > https://stat.ethz.ch/mailman/listinfo/r-help > PLEASE do read the posting guide http://www.R-project.org/posting-guide.html > and provide commented, minimal, self-contained, reproducible code. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] Installing package
Using install packages pull-down, I chose a mirror and then package rJava. Then it said that it cannot remove the rJava package already installed. Then when I typed library(rJava) it said there was no rjava package. Isn't that rather contradictory for R? -- View this message in context: http://r.789695.n4.nabble.com/Installing-package-tp3510987p3510987.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Weird read.xls behavior
Kenneth, Thanks for the reply. I checked the original data. There is no space. I even manually added a space to one value. After reading in with read.xls, the value has two spaces. The reason I don't like it is I am going to do some comparison with another dataset, which is supposed to be the same as this one. Now I am getting a bunch of false negatives. Jun On Mon, May 9, 2011 at 11:01 PM, Kenneth Roy Cabrera Torres < krcab...@une.net.co> wrote: > Maybe in the original there are some "ghost" spaces after ng/ml, > verify them. > > Any way you can erase the first and the last white spaces with gsub > function. > > HTH > > Kenneth > El lun, 09-05-2011 a las 22:44 -0500, Jun Shen escribió: > > Dear list, > > > > I used read.xls to read in an excel file, which has both character and > > numeric columns. Everything seems fine except in the last column, I have > > this character value "ng/ml". When reading in, read.xls seems to add a > space > > at the end of it, became "ng/ml ". How can I prevent read.xls doing so? > > Thanks. > > > > >read.xls(data, header=T, as.is=T) > > > > Jun > > > > [[alternative HTML version deleted]] > > > > __ > > R-help@r-project.org mailing list > > https://stat.ethz.ch/mailman/listinfo/r-help > > PLEASE do read the posting guide > http://www.R-project.org/posting-guide.html > > and provide commented, minimal, self-contained, reproducible code. > > > [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Weird read.xls behavior
Maybe in the original there are some "ghost" spaces after ng/ml, verify them. Any way you can erase the first and the last white spaces with gsub function. HTH Kenneth El lun, 09-05-2011 a las 22:44 -0500, Jun Shen escribió: > Dear list, > > I used read.xls to read in an excel file, which has both character and > numeric columns. Everything seems fine except in the last column, I have > this character value "ng/ml". When reading in, read.xls seems to add a space > at the end of it, became "ng/ml ". How can I prevent read.xls doing so? > Thanks. > > >read.xls(data, header=T, as.is=T) > > Jun > > [[alternative HTML version deleted]] > > __ > R-help@r-project.org mailing list > https://stat.ethz.ch/mailman/listinfo/r-help > PLEASE do read the posting guide http://www.R-project.org/posting-guide.html > and provide commented, minimal, self-contained, reproducible code. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] Weird read.xls behavior
Dear list, I used read.xls to read in an excel file, which has both character and numeric columns. Everything seems fine except in the last column, I have this character value "ng/ml". When reading in, read.xls seems to add a space at the end of it, became "ng/ml ". How can I prevent read.xls doing so? Thanks. >read.xls(data, header=T, as.is=T) Jun [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] SQP with Constraints
Look at the solve.QP() function in the "quadprog" package. Ravi. From: r-help-boun...@r-project.org [r-help-boun...@r-project.org] On Behalf Of vioravis [viora...@gmail.com] Sent: Monday, May 09, 2011 10:46 PM To: r-help@r-project.org Subject: [R] SQP with Constraints I am trying to optimize function similar to the following: Minimize x1^2 - x2^2 - x3^2 st x1 < x2 x2 < x3 The constraint is that the variables should be monotonically increasing. Is there any package that implements Sequential Quadratic Programming with ability include these constraints??? Thanks you. Ravi -- View this message in context: http://r.789695.n4.nabble.com/SQP-with-Constraints-tp3510857p3510857.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] SQP with Constraints
I am trying to optimize function similar to the following: Minimize x1^2 - x2^2 - x3^2 st x1 < x2 x2 < x3 The constraint is that the variables should be monotonically increasing. Is there any package that implements Sequential Quadratic Programming with ability include these constraints??? Thanks you. Ravi -- View this message in context: http://r.789695.n4.nabble.com/SQP-with-Constraints-tp3510857p3510857.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] Saving multiple 3x3 TIFF graphics inside a loop
Dear Friends,
I have been trying to save multiple 3x3 (mfrow=c(3,3) graphics inside a loop
using tiff figure format (not using PDF or savePlot functions) with no
success. Could you please help?
Here is a simplified example code:
dat=data.frame (ID=rep(1:10,each=10),IDV=rep(seq(1:10),times=10))
dat$DV <- with(dat, 50+15*IDV)
dat=dat[order(dat$ID,dat$IDV),]
for(i in 1:10){
dt1 = dat[dat$ID==i,]
pagei=as.integer(ceiling(i/9))
#This does not work
if(i==1) {tiff(file=paste("Outfile",pagei,".tiff",sep="")
,width=17.15,height=17.15,units="cm", res=1200, pointsize=10,
compression = "lzw")}
if(i==10) {tiff(file=paste("Outfile",pagei,".tiff",sep="")
,width=17.15,height=17.15,units="cm", res=1200, pointsize=10,
compression = "lzw")}
par(mar=c(5,5,4,1),mfrow=c(3,3))
plot(dt1[, "IDV"],dt1[, "DV"], type="n")
lines(dt1[, "IDV"], dt1[, "DV"], type="b", col=1,lwd=3,pch=1)
title(paste(i),col=8,cex=.8)
if(i==9) dev.off ## close file
}
dev.off()
The idea is to save 2 files with 3x3 layouts but I only get one subject in
Outfile1.
OS: Windows 7 64 bits
R version 2.13.0
Many Thanks,
John
[[alternative HTML version deleted]]
__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Re: [R] save and load user modifications of options
Thanks David! I got a solution, though maybe not optimal. In the zzz.r file
of the R package, I include the folloing code:
.onLoad <- function(libname,pkgname) {
myoptions <- list(ngs.python="sage -python",ngs.macs="macs14")
if(exists("myoptions",.GlobalEnv))
options(.GlobalEnv$myoptions)
else
options(myoptions)
}
If user save his options in the myoptions list, by loading saved image he
does not need to set the option again. However, I still believe there is a
more elegant way to let user save his options. Hope someone could come up
with a better solution :-)
Thanks!
Xue
On Sat, May 7, 2011 at 5:47 AM, David Winsemius wrote:
>
> On May 6, 2011, at 8:59 PM, xwang14 wrote:
>
> Hi,
>>
>> Could anyone help me with the following problem? After I finished a R
>> session and modified some options (for example, set
>> options(editor="neditor")), I want save these modifications so that after
>> I
>> load the saved R data I do not need to modify these options again. What is
>> the best way to do this? Is there a way without using an external file? I
>> tried save.image. However, only default setting is perserved.
>>
>
> You need to read about your options about setting options at startup. You
> can find information in the Installation Manual or by typing: ?Startup
>
> (I cannot think of a manner in which this can be tied to a data file being
> loaded.)
>
> --
>
> David Winsemius, MD
> West Hartford, CT
>
>
[[alternative HTML version deleted]]
__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Re: [R] Question Using Old R Packages
In case anyone else is having similar problems, it turns out it may have been an issue with the interface I was using (R Studio). When I close R Studio and tried it again through R it installed without the error message. Chris. -- View this message in context: http://r.789695.n4.nabble.com/Question-Using-Old-R-Packages-tp3510721p3510726.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] Question Using Old R Packages
I'm trying to use the package rgl for a research project. I've used it in the past, but now when I try to re-install it after updating to R 2.13.0 I'm getting the following error: Warning in install.packages : package ‘rgl’ is not available (for R version 2.13.0) Is there any way to get R to recognize this package, or am I going to have to re-install an old version of R to use it? Thanks in advance, Chris. -- View this message in context: http://r.789695.n4.nabble.com/Question-Using-Old-R-Packages-tp3510721p3510721.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] Reading a large netCDF file using R
I got a netCDF file from a climate group and wanted to aggregate the data.
The file summary looks like this
library(ncdf)
nc=open.ncdf("NCEP_prec_1949_58.nc")
> nc
[1] "file NCEP_prec_1949_58.nc has 4 dimensions:"
[1] "Time Size: 14608"
[1] "lat Size: 99"
[1] "lon Size: 199"
[1] "DateStrLen Size: 20"
[1] ""
[1] "file NCEP_prec_1949_58.nc has 1 variables:"
[1] "float Prec[lon,lat,Time] Longname:yearly accumulated precip
Missval:1e+30"
I tried to get the variable values using this command
> xx=get.var.ncdf(nc)
Error: cannot allocate vector of size 2.1 Gb
This file has six hourly data for the 199 x 99 points for 10 years. I wanted
to aggregate this data into a monthly scale. I tried used a simple code like
this
for (i in 1:noofdays) {
for (j in 0:3) {
x= get.var.ncdf(nc,v1,start=c(1,1,(i+j)),count=c(199,99,1))
temp_data_mat=temp_data_mat+x
}
for (x1 in 1:199) {
for (x2 in 1:99) {
data_mat_89_99[x1,x2,ctr]=temp_data_mat[x1,x2]
}
}
ctr=ctr+1
temp_data_mat=matrix(0,ncol=99,nrow=199)
}
I didnt think it worked... can u suggest me some other way ... I could not
use the start and count properly
--
View this message in context:
http://r.789695.n4.nabble.com/Reading-a-large-netCDF-file-using-R-tp3510762p3510762.html
Sent from the R help mailing list archive at Nabble.com.
__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Re: [R] Creating Observation ID
Here is one way:
df <- data.frame(Value = rnorm(30),
Group = sample(c('A','B','C'), 30,
replace = TRUE))
## make a little function to do the job
iNumber <- function(f) {
f <- as.factor(f)
X <- outer(f, levels(f), "==")+0
rowSums(X * apply(X, 2, cumsum))
}
## add the numbering column
df <- within(df, internalNumber <- iNumber(Group))
## Check that it works
> head(df)
Value Group internalNumber
1 -1.5014788 C 1
2 0.6035679 C 2
3 -0.6953930 C 3
4 -0.2413863 A 1
5 -0.1170961 A 2
6 1.5110721 C 4
-Original Message-
From: r-help-boun...@r-project.org [mailto:r-help-boun...@r-project.org] On
Behalf Of Robert Baer
Sent: Tuesday, 10 May 2011 7:22 AM
To: R-help@r-project.org
Subject: [R] Creating Observation ID
If I have a data frame something like:
Value=rnorm(30)
Group = sample(c('A','B','C'), 30, replace=TRUE)
df = data.frame(Value, Group)
It seems like it should be simple to create an 'ObsID' column which indicates
the observation order of each Value within each of the 3 groups. Somehow, I
can't quite see how to do it without manually sub-setting the parent data frame
and then putting it back together again.
Anyone able to get me started on a cleaner (more R-like) approach?
Thanks,
Rob
--
Robert W. Baer, Ph.D.
Professor of Physiology
Kirksville College of Osteopathic Medicine
A. T. Still University of Health Sciences
800 W. Jefferson St.
Kirksville, MO 63501
660-626-2322
FAX 660-626-2965
[[alternative HTML version deleted]]
__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
[R] Lattice: splom plots for different factors with correlation in lower.panel
Hello list,
I am looking to create a figure for my dataset using splom, where there is a
splom subplot for each level of a factor within, for example, a 2x2 layout.
For each subplot, I wish to put the r-value between each variable pair in
the lower panel. The code I have thus far is below, using the iris dataset
so that it is reproducible. This almost does what I want, but for some
reason overlays the r-values for each level in each subplot.
I think the problem is something to do with the lower.panel function call
within my custom function, but I am not a huge whizz using lattice and can't
figure out what it is. If I put the panel.text call in the lower.panel
function, it only causes a similar problem. Apologies if there is something
obvious I have missed, I hope there is someone out there who can help me!
var.cor <- list()
for(i in 1:3){
var.cor[[i]] <- abs(cor(subset(iris[1:4], iris$Species ==
levels(iris$Species)[i]))) #calculate variable correlation for each species
var.cor[[i]] <- data.frame(values = as.vector(var.cor[[i]]), row =
as.vector(row(var.cor[[i]])), col = as.vector(col(var.cor[[i]])))
var.cor[[i]] <- subset(var.cor[[i]], colhttp://r.789695.n4.nabble.com/Lattice-splom-plots-for-different-factors-with-correlation-in-lower-panel-tp3510452p3510452.html
Sent from the R help mailing list archive at Nabble.com.
__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Re: [R] Fortran Symbol Name not in Load Table
I used the DLL export viewer to what is the table name being exported. It is showing as VALUEAHROPTIMIZE_. This is the name of the function we have used plus the underscore. Is there any other reason for the function not getting recognized??? Thanks. -- View this message in context: http://r.789695.n4.nabble.com/Fortran-Symbol-Name-not-in-Load-Table-tp3509852p3510761.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Filtering out bad data points
You could use a function to do the job:
withinRange <- function(x, r = quantile(x, c(0.05, 0.95)))
x >= r[1] & x <= r[2]
dtest2 <- subset(dftest, withinRange(x))
-Original Message-
From: r-help-boun...@r-project.org [mailto:r-help-boun...@r-project.org] On
Behalf Of Robert A'gata
Sent: Tuesday, 10 May 2011 10:57 AM
To: r-help@r-project.org
Subject: [R] Filtering out bad data points
Hi,
I always have a question about how to do this best in R. I have a data
frame and a set of criteria to filter points out. My procedure is to
always locate indices of those points, check if index vector length is
greater than 0 or not and then remove them. Meaning
dftest <- data.frame(x=rnorm(100),y=rnorm(100));
qtile <- quantile(dftest$x,probs=c(0.05,0.95));
badIdx <- which((dftest$x < qtile[1]) | (dftest$x > qtile[2]));
if (length(badIdx) > 0) {
dftest <- dftest[-idx,];
}
My question is that is there a more streamlined way to achieve this? Thank you.
Cheers,
Robert
__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
[R] Filtering out bad data points
Hi,
I always have a question about how to do this best in R. I have a data
frame and a set of criteria to filter points out. My procedure is to
always locate indices of those points, check if index vector length is
greater than 0 or not and then remove them. Meaning
dftest <- data.frame(x=rnorm(100),y=rnorm(100));
qtile <- quantile(dftest$x,probs=c(0.05,0.95));
badIdx <- which((dftest$x < qtile[1]) | (dftest$x > qtile[2]));
if (length(badIdx) > 0) {
dftest <- dftest[-idx,];
}
My question is that is there a more streamlined way to achieve this? Thank you.
Cheers,
Robert
__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Re: [R] Stirlings Approximation
?lchoose ?lgamma ?lfactorial On Mon, May 9, 2011 at 7:45 PM, Jim Silverton wrote: > I have some big combinations like: > choose 784645433 > > Can R compute these? > Is there any package that does stirlings approximation in R? > > -- > Thanks, > Jim. > > [[alternative HTML version deleted]] > > __ > R-help@r-project.org mailing list > https://stat.ethz.ch/mailman/listinfo/r-help > PLEASE do read the posting guide http://www.R-project.org/posting-guide.html > and provide commented, minimal, self-contained, reproducible code. > __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Stirlings Approximation
I have some big combinations like: choose 784645433 Can R compute these? Is there any package that does stirlings approximation in R? -- Thanks, Jim. [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] Help with options("contrasts")
Dear list, Is it possible to specify a contrast in options() that would create an identity matrix for each factor in the model matrix? For example, for each factor in 'dd' below, I can create an identity matrix using contrasts = FALSE. Is it possible to set this in options(), so when I create a model matrix from any factor, the factor coding would follow this specification for the contrast? dd <- data.frame(a = gl(3,4), b = gl(4,1,12)) ca <- contrasts(dd$a, contrasts= FALSE) # 3 x 3 identity matrix cb <- contrasts(dd$b, contrasts= FALSE) # 4 x 4 identity matrix My attempt below works fine, but again, I'd like to specify this in the options() as opposed to each contrast individually. model.matrix(~ a + b, dd, contrasts =list(a=ca, b=cb)) Thanks for any help! Axel. [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Setting NA to blank
I asked because I thought it'd solve an issue I had. I was actually being quite rash in asking this question and for that, I apologize. I wanted to know because I was attempting to create a heatmap where the NA values would not be shown while all the outputs with actual numerical value will be shown. I had assumed that setting the NA's to blanks would fix the issue, but it hadn't. I refrained from immediately asking another question so I that I can look further into this. I hope that answers your question. On Mon, May 9, 2011 at 4:21 PM, Ted Harding wrote: > John Kane's reply sums it up! (Though you could use "", > instead of " ", which would give you an "empty string" > instead of the "space" character; but the resulting > matrix would still consist entirely of "character" > elements). > > However, the real reason I am following up is to ask > why you want the blank instead of the NA. > > If it is just for printing out or display, then the > fact that the matrix has been converted to character > probably does not matter. > > But if it is for compatibility with some other > computational software that (e.g.) expects missing > values to be represented by a blank, or some "null" > representation, then it may not be so straightforward. > > So, if that might be an issue, please describe for us > how you intend to use the result. > > Ted. > > On 09-May-11 19:56:39, Dat Mai wrote: > > Thank you kind sir! > > > > On Mon, May 9, 2011 at 3:25 PM, John Kane wrote: > > > >> > >> (mat <- matrix(c(1,2,3,NA),2)) > >> mat[is.na(mat)] <- " " > >> mat > >> > >> But if you have a numerical matrix it coverts the matrix to character. > >> > >> --- On Mon, 5/9/11, Dat Mai wrote: > >> > >> > From: Dat Mai > >> > Subject: [R] Setting NA to blank > >> > To: r-help@r-project.org > >> > Received: Monday, May 9, 2011, 2:46 PM > >> > Hey All, > >> > > >> > I have a matrix m, and I wish to set all the NA values to > >> > blank. How would I > >> > do so? > >> > > >> > -- > >> > Best, > >> > Dat Mai > >> > PhD Rotation Student > >> > Albert Einstein College of Medicine > > > E-Mail: (Ted Harding) > Fax-to-email: +44 (0)870 094 0861 > Date: 09-May-11 Time: 21:21:07 > -- XFMail -- > -- Best, Dat Mai PhD Rotation Student Albert Einstein College of Medicine [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Creating Observation ID
Does the following work for you?
> df2 <- transform(df, ObsID=ave(rep(0,length(Group)), Group,
FUN=seq_along))
> head(df2)
Value Group ObsID
1 -0.0025132 B 1
2 -1.2456156 A 1
3 -2.0531704 B 2
4 1.5861770 B 3
5 0.1900908 A 2
6 0.7197067 B 4
Bill Dunlap
Spotfire, TIBCO Software
wdunlap tibco.com
> -Original Message-
> From: r-help-boun...@r-project.org
> [mailto:r-help-boun...@r-project.org] On Behalf Of Robert Baer
> Sent: Monday, May 09, 2011 2:22 PM
> To: R-help@r-project.org
> Subject: [R] Creating Observation ID
>
> If I have a data frame something like:
> Value=rnorm(30)
> Group = sample(c('A','B','C'), 30, replace=TRUE)
> df = data.frame(Value, Group)
>
> It seems like it should be simple to create an 'ObsID' column
> which indicates the observation order of each Value within
> each of the 3 groups. Somehow, I can't quite see how to do
> it without manually sub-setting the parent data frame and
> then putting it back together again.
>
> Anyone able to get me started on a cleaner (more R-like) approach?
>
> Thanks,
>
> Rob
>
> --
> Robert W. Baer, Ph.D.
> Professor of Physiology
> Kirksville College of Osteopathic Medicine
> A. T. Still University of Health Sciences
> 800 W. Jefferson St.
> Kirksville, MO 63501
> 660-626-2322
> FAX 660-626-2965
>
> [[alternative HTML version deleted]]
>
> __
> R-help@r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide
> http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.
>
__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
[R] Creating Observation ID
If I have a data frame something like:
Value=rnorm(30)
Group = sample(c('A','B','C'), 30, replace=TRUE)
df = data.frame(Value, Group)
It seems like it should be simple to create an 'ObsID' column which indicates
the observation order of each Value within each of the 3 groups. Somehow, I
can't quite see how to do it without manually sub-setting the parent data frame
and then putting it back together again.
Anyone able to get me started on a cleaner (more R-like) approach?
Thanks,
Rob
--
Robert W. Baer, Ph.D.
Professor of Physiology
Kirksville College of Osteopathic Medicine
A. T. Still University of Health Sciences
800 W. Jefferson St.
Kirksville, MO 63501
660-626-2322
FAX 660-626-2965
[[alternative HTML version deleted]]
__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Re: [R] interrupted time series analysis using ARIMA models
Look at: de Jong, P. and Penzer, J. (1998) Diagnosing shocks in time series. Journal of the American Statistical Association. 93, 796-806. A pdf is available at: http://stats.lse.ac.uk/penzer/publications.html -Roy M. On May 9, 2011, at 1:32 PM, jpehsani wrote: > Hi Berta, > > Did you have any luck finding code for the gradual permanent impact > intervention? > > I am trying to fit two types of intervention effects for two different > models - a gradual and a sudden impact effect - and unable to find any code > on how to do this. > thanks > Jon > > -- > View this message in context: > http://r.789695.n4.nabble.com/interrupted-time-series-analysis-using-ARIMA-models-tp794821p3510253.html > Sent from the R help mailing list archive at Nabble.com. > > __ > R-help@r-project.org mailing list > https://stat.ethz.ch/mailman/listinfo/r-help > PLEASE do read the posting guide http://www.R-project.org/posting-guide.html > and provide commented, minimal, self-contained, reproducible code. ** "The contents of this message do not reflect any position of the U.S. Government or NOAA." ** Roy Mendelssohn Supervisory Operations Research Analyst NOAA/NMFS Environmental Research Division Southwest Fisheries Science Center 1352 Lighthouse Avenue Pacific Grove, CA 93950-2097 e-mail: roy.mendelss...@noaa.gov (Note new e-mail address) voice: (831)-648-9029 fax: (831)-648-8440 www: http://www.pfeg.noaa.gov/ "Old age and treachery will overcome youth and skill." "From those who have been given much, much will be expected" __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] maximum likelihood convergence reproducing Anderson Blundell 1982 Econometrica R vs Stata
Wow that is really interesting, Sorry I was asleep when you emailed these. And yes, of course, I had been trying to implement model 18, not 18s, that was a typo, sorry. I will have a look at the code you posted. Thanks, Alex On 10 May 2011 02:18, peter dalgaard wrote: > Hmm, I tried replacing the x's in the model with their principal component > scores, and suddenly everything converges as a greased lightning: > >> Z <- princomp(cbind(x1,x2,x3))$scores >> Z <- as.data.frame(princomp(cbind(x1,x2,x3))$scores) >> names(Z)<- letters[1:3] >> optimx(rep(0,8),lnl, hessian=TRUE, y1=y1, y2=y2, > + x1=Z$a, x2=Z$b, x3=Z$c, method="BFGS") > > par > 1 0.59107682, 0.01043568, -0.20639153, 0.25902746, 0.24675162, -0.01426477, > 0.18045177, -0.23657327 > fvalues method fns grs itns conv KKT1 KKT2 xtimes > 1 -76.73878 BFGS 157 37 NULL 0 TRUE TRUE 0.055 > Warning messages: > 1: In max(logpar) : no non-missing arguments to max; returning -Inf > 2: In min(logpar) : no non-missing arguments to min; returning Inf > > The likelihood appears to be spot on, but, obviously, the parameter estimates > need to be back-transformed to the original x1,x2,x3 system. I'll leave that > as the proverbial "exercise for the reader"... > > However, the whole thing leads me to a suspicion that maybe our numerical > gradients are misbehaving in cases with high local collinearity? > > -pd > > On May 9, 2011, at 13:40 , Alex Olssen wrote: > >> Hi Mike, >> >> Mike said >> "is this it, page 1559?" >> >> That is the front page yes, page 15*6*9 has the table, of which the >> model labelled 18s is the one I replicated. >> >> "did you actually cut/paste code anywhere and is your first >> coefficient -.19 or -.019? >> Presumably typos would be one possible problem." >> >> -0.19 is not a typo, it is pi10 in the paper, and a1 in my Stata >> estimation - as far as I can tell cutting and pasting is not the >> problem. >> >> "generally it helps if we could at least see the equations to check your >> code against typos ( note page number ?) in lnl that may fix part of the >> mystery. Is full text available >> on author's site, doesn't come up on citeseer AFAICT," >> >> Unfortunately I do not know of any place to get the full version of >> this paper that doesn't require access to a database such as JSTOR. >> The fact that this likelihood function reproduces the published >> results in Stata makes me confident that it is correct - I also have >> read a lot on systems estimation and it is a pretty standard >> likelihood function. >> >> "I guess one question would be " what is beta" in lnl supposed to be - >> it isn't used anywhere but I will also mentioned I'm not that familiar >> with the R code ( I'm trying to work through this to learn R and the >> optimizers). >> >> maybe some words would help, is sigma supposed to be 2x2 or 8x8 and what are >> e1 and e2 supposed to be?" >> >> The code above is certainly not as elegant as it could be - in this >> case the beta is rather superfluous. It is just a vector to hold >> parameters - but since I called all the parameters theta anyway there >> is no need for it. e1 and e2 are the residuals from the first and >> second equations of the system. Sigma is a 2x2 matrix which is the >> outer product of the two vectors of residuals. >> >> Kind regards, >> >> Alex >> >> >> >> On 9 May 2011 23:12, Mike Marchywka wrote: >>> >>> >>> >>> >>> >>> >>> Date: Mon, 9 May 2011 22:06:38 +1200 From: alex.ols...@gmail.com To: pda...@gmail.com CC: r-help@r-project.org; da...@otter-rsch.com Subject: Re: [R] maximum likelihood convergence reproducing Anderson Blundell 1982 Econometrica R vs Stata Peter said "Ahem! You might get us interested in your problem, but not to the level that we are going to install Stata and Tsp and actually dig out and study the scientific paper you are talking about. Please cite the results and explain the differences." Apologies Peter, will do, The results which I can emulate in Stata but not (yet) in R are reported below. >>> >>> did you actually cut/paste code anywhere and is your first coefficient -.19 >>> or -.019? >>> Presumably typos would be one possible problem. >>> They come from Econometrica Vol. 50, No. 6 (Nov., 1982), pp. 1569 >>> >>> >>> is this it, page 1559? >>> >>> http://www.jstor.org/pss/1913396 >>> >>> generally it helps if we could at least see the equations to check your >>> code against typos ( note page number ?) in lnl that may fix part of the >>> mystery. Is full text available >>> on author's site, doesn't come up on citeseer AFAICT, >>> >>> >>> http://citeseerx.ist.psu.edu/search?q=blundell+1982&sort=ascdate >>> >>> I guess one question would be " what is beta" in lnl supposed to be - >>> it isn't used anywhere but I will also m
Re: [R] interrupted time series analysis using ARIMA models
Hi Berta, Did you have any luck finding code for the gradual permanent impact intervention? I am trying to fit two types of intervention effects for two different models - a gradual and a sudden impact effect - and unable to find any code on how to do this. thanks Jon -- View this message in context: http://r.789695.n4.nabble.com/interrupted-time-series-analysis-using-ARIMA-models-tp794821p3510253.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Averaging uneven measurements by time with uneven numbers of measurements
An easy way to average every 30 minutes is using the aggregate function. First I use the mod (%%) to get times as the next earliest possible 30 min time increment. bTime<- as.POSIXct(c( "2011-04-28 09:02:00 CDT","2011-04-28 09:02:00 CDT","2011-04-28 09:12:00 CDT","2011-04-28 09:14:00 CDT","2011-04-28 09:15:00 CDT","2011-04-28 09:23:00 CDT","2011-04-28 09:45:00 CDT","2011-04-28 09:53:00 CDT","2011-04-28 10:03:00 CDT")) numTime<-as.numeric(bTime)-21600 Weight<-runif(9)*100 minT<-30 excess<-numTime %% (minT*60) nTime<-numTime-excess nDateT<-as.POSIXct(nTime, origin="1970-01-01",tz= "US/Central") meanw <- aggregate(Weight, list(nDateT), mean, na.rm = TRUE) -Original Message- From: cl...@ecy.wa.gov [mailto:cl...@ecy.wa.gov] Sent: Thursday, May 05, 2011 03:58 PM To: Thompson, Adele - adele_thomp...@cargill.com Cc: r-help@r-project.org Subject: Re: [R] Averaging uneven measurements by time with uneven numbers of measurements In your first request for help you said, "How do I average the measurements by every 30 minutes?" With 25000 readings over three days, it looks as if you are getting readings just about every second. Okay, why don't you use the first reading as your initial weight, w0. Then subtract each succeeding reading from that to obtain the amount of feed dispensed. Now plot that value every 30 minutes. If you are interested in the variation of feed dispensed over a half hour interval, that can be easily obtained by accummulating those half-hour readings. -- Clint BowmanINTERNET: cl...@ecy.wa.gov Air Quality Modeler INTERNET: cl...@math.utah.edu Department of Ecology VOICE: (360) 407-6815 PO Box 47600FAX:(360) 407-7534 Olympia, WA 98504-7600 USPS: PO Box 47600, Olympia, WA 98504-7600 Parcels:300 Desmond Drive, Lacey, WA 98503-1274 On Thu, 5 May 2011, Schatzi wrote: > I do not want smoothing as the data should have jumps (it is weight left in > feeding bunker). I was thinking of maybe using a histogram-like function and > then averaging that. Not sure if this is possible. > > - > In theory, practice and theory are the same. In practice, they are not - > Albert Einstein > -- > View this message in context: > http://r.789695.n4.nabble.com/Averaging-uneven-measurements-by-time-with-uneven-numbers-of-measurements-tp3499337p3499386.html > Sent from the R help mailing list archive at Nabble.com. > > __ > R-help@r-project.org mailing list > https://stat.ethz.ch/mailman/listinfo/r-help > PLEASE do read the posting guide http://www.R-project.org/posting-guide.html > and provide commented, minimal, self-contained, reproducible code. > __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Setting NA to blank
John Kane's reply sums it up! (Though you could use "", instead of " ", which would give you an "empty string" instead of the "space" character; but the resulting matrix would still consist entirely of "character" elements). However, the real reason I am following up is to ask why you want the blank instead of the NA. If it is just for printing out or display, then the fact that the matrix has been converted to character probably does not matter. But if it is for compatibility with some other computational software that (e.g.) expects missing values to be represented by a blank, or some "null" representation, then it may not be so straightforward. So, if that might be an issue, please describe for us how you intend to use the result. Ted. On 09-May-11 19:56:39, Dat Mai wrote: > Thank you kind sir! > > On Mon, May 9, 2011 at 3:25 PM, John Kane wrote: > >> >> (mat <- matrix(c(1,2,3,NA),2)) >> mat[is.na(mat)] <- " " >> mat >> >> But if you have a numerical matrix it coverts the matrix to character. >> >> --- On Mon, 5/9/11, Dat Mai wrote: >> >> > From: Dat Mai >> > Subject: [R] Setting NA to blank >> > To: r-help@r-project.org >> > Received: Monday, May 9, 2011, 2:46 PM >> > Hey All, >> > >> > I have a matrix m, and I wish to set all the NA values to >> > blank. How would I >> > do so? >> > >> > -- >> > Best, >> > Dat Mai >> > PhD Rotation Student >> > Albert Einstein College of Medicine E-Mail: (Ted Harding) Fax-to-email: +44 (0)870 094 0861 Date: 09-May-11 Time: 21:21:07 -- XFMail -- __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Create subsets of data
On May 9, 2011, at 3:46 PM, David Winsemius wrote: On May 9, 2011, at 9:40 AM, Pavan G wrote: Hello All, Let's say I have points on a x-y plane. x ranges from 0-2 and y from 0-2. There are points in quadrants x[0:1]---y[0:1] and in x[1:2] y[1:2]. I would like to get the mean and std of the points in the x[0:1] y[0:1] quadrant alone. Is there a straight forward way to do it? I am assuming that you have yet a third vector that has values at each of those coordinates and it is that set of categorized values for which you want the means and std deviations: I will exemplify the use of tapply on cut()-igorized vectors and a z-value which is the L1 distance from the origin. (Actually, after checking help(dist) I think the sum(x_i) is called the Canberra distance. ) (And excuse the earlier feeble attempt at humor); > x <- runif(2000, 0,2) > y <- runif(2000, 0, 2) > xc <- cut(x, c(0,1,2)) > yc <- cut(y, c(0,1,2)) > z <- x+y > tapply(z, list(xc,yc), mean) (0,1](1,2] (0,1] 1.013192 2.016095 (1,2] 1.979930 2.996229 # seems to make sense > tapply(z, list(xc,yc), sd) (0,1] (1,2] (0,1] 0.4028310 0.4133113 (1,2] 0.4239014 0.3984559 # also seems sensible -- David Winsemius, MD West Hartford, CT __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Setting NA to blank
Thank you kind sir! On Mon, May 9, 2011 at 3:25 PM, John Kane wrote: > > (mat <- matrix(c(1,2,3,NA),2)) > mat[is.na(mat)] <- " " > mat > > But if you have a numerical matrix it coverts the matrix to character. > > --- On Mon, 5/9/11, Dat Mai wrote: > > > From: Dat Mai > > Subject: [R] Setting NA to blank > > To: r-help@r-project.org > > Received: Monday, May 9, 2011, 2:46 PM > > Hey All, > > > > I have a matrix m, and I wish to set all the NA values to > > blank. How would I > > do so? > > > > -- > > Best, > > Dat Mai > > PhD Rotation Student > > Albert Einstein College of Medicine > > -- Best, Dat Mai PhD Rotation Student Albert Einstein College of Medicine [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Create subsets of data
On May 9, 2011, at 9:40 AM, Pavan G wrote: Hello All, Let's say I have points on a x-y plane. x ranges from 0-2 and y from 0-2. There are points in quadrants x[0:1]---y[0:1] and in x[1:2] y[1:2]. I would like to get the mean and std of the points in the x[0:1] y[0:1] quadrant alone. Is there a straight forward way to do it? I am assuming that you have yet a third vector that has values at each of those coordinates and it is that set of categorized values for which you want the means and std deviations: I will exemplify the use of tapply on cut()-igorized vectors and a z-value which is the L1 distance from the origin. (And excuse the earlier feeble attempt at humor); > x <- runif(2000, 0,2) > y <- runif(2000, 0, 2) > xc <- cut(x, c(0,1,2)) > yc <- cut(y, c(0,1,2)) > z <- x+y > tapply(z, list(xc,yc), mean) (0,1](1,2] (0,1] 1.013192 2.016095 (1,2] 1.979930 2.996229 # seems to make sense > tapply(z, list(xc,yc), sd) (0,1] (1,2] (0,1] 0.4028310 0.4133113 (1,2] 0.4239014 0.3984559 # also seems sensible -- David Winsemius, MD West Hartford, CT __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Using NULL to my data?
Dear Gabor,
Thanks for your help. I was trying to do what you ask me and I've found the
solution.
> with(teste,sprintf("INSERT INTO OBS (date,T_2M,TMAX_2M,TMIN_2M) VALUES
(%s, %5.2f, %5.2f, %5.2f,%s)",date2,T_2M,TMAX_2M,TMIN_2M,Station_NO))
Error in sprintf("INSERT INTO OBS (date,T_2M,TMAX_2M,TMIN_2M) VALUES (%s,
%5.2f, %5.2f, %5.2f,%s)", :
invalid format '%5.2f'; use format %s for character objects
>
>
> with(teste,sprintf("INSERT INTO OBS (date,T_2M,TMAX_2M,TMIN_2M) VALUES
(%s, %s, %s, %s,%s)",date2,T_2M,TMAX_2M,TMIN_2M,Station_NO))
[1] "INSERT INTO OBS (date,T_2M,TMAX_2M,TMIN_2M) VALUES (2011042912, 22.5,
NULL, 22.4,820420)"
[2] "INSERT INTO OBS (date,T_2M,TMAX_2M,TMIN_2M) VALUES (2011042912, 26.9,
NULL, 23.4,820980)"
[3] "INSERT INTO OBS (date,T_2M,TMAX_2M,TMIN_2M) VALUES (2011042912, 24.3,
NULL, 23.3,821130)"
[4] "INSERT INTO OBS (date,T_2M,TMAX_2M,TMIN_2M) VALUES (2011042912, 24.4,
NULL, 23.7,821410)"
[5] "INSERT INTO OBS (date,T_2M,TMAX_2M,TMIN_2M) VALUES (2011042912, 28.2,
NULL, 21.1,821450)"
[6] "INSERT INTO OBS (date,T_2M,TMAX_2M,TMIN_2M) VALUES (2011042912, 23.3,
NULL, 22.8,821810)"
On Mon, May 9, 2011 at 2:05 PM, Gabor Grothendieck
wrote:
> On Mon, May 9, 2011 at 12:59 PM, Nilza BARROS
> wrote:
> > Hi, Thanks for your attentio.
> >
> > I have the data frame below:
> >
> >> head(Alldados)
> > Station_NO date1 T_2M TMAX_2M TMIN_2M TD_2M PS FF_10M DD_10M
> > 1 820420 110429/1200 22.5NULL22.4 22.2 NULL 0 0
> > 2 820980 110429/1200 26.9NULL23.4 24.1 1010.2 2.91360
> > 3 821130 110429/1200 24.3NULL23.3 23.7 NULL 1.94230
> > 4 821410 110429/1200 24.4NULL23.7 24.2 1011.8 2.91270
> > 5 821450 110429/1200 28.2NULL21.1 25.8 1008.8 0 0
> > 6 821810 110429/1200 23.3NULL22.8 22.9 1001.6 0 0
> > TOT_PRCP CLCL date2
> > 184.00 NULL 2011042912
> > 2 2.00 NULL 2011042912
> > 3 3.00 NULL 2011042912
> > 412.00 NULL 2011042912
> > 5 6.00 NULL 2011042912
> > 638.00 NULL 2011042912
> >
> > Now each line will feed my database. So I need to format each line like
> > below:
> >
> > ===
> > [1] "INSERT INTO OBS
> >
> (date,T_2M,TMAX_2M,TMIN_2M,TD_2M,PS,FF_10M,DD_10M,TOT_PRCP,CLCL,Station_NO)
> > VALUES (2011042912, 22.50,NA, 22.40,22.20, NA, 0.00, 0.00,36.00,
> > NA,820420)"
> > [2] "INSERT INTO OBS
> >
> (date,T_2M,TMAX_2M,TMIN_2M,TD_2M,PS,FF_10M,DD_10M,TOT_PRCP,CLCL,Station_NO)
> > VALUES (2011042912, 26.90,NA, 23.40,24.10,1010.20, 2.91,360.00,16.00,
> > NA,820980)"
> > [3] "INSERT INTO OBS
> >
> (date,T_2M,TMAX_2M,TMIN_2M,TD_2M,PS,FF_10M,DD_10M,TOT_PRCP,CLCL,Station_NO)
> > VALUES (2011042912, 24.30,NA, 23.30,23.70, NA, 1.94,230.00,19.00,
> > NA,821130)"
> > [4] "INSERT INTO OBS
> >
> (date,T_2M,TMAX_2M,TMIN_2M,TD_2M,PS,FF_10M,DD_10M,TOT_PRCP,CLCL,Station_NO)
> > VALUES (2011042912, 24.40,NA, 23.70,24.20,1011.80, 2.91,270.00,12.00,
> > NA,821410)"
> > [5] "INSERT INTO OBS
> >
> (date,T_2M,TMAX_2M,TMIN_2M,TD_2M,PS,FF_10M,DD_10M,TOT_PRCP,CLCL,Station_NO)
> > VALUES (2011042912, 28.20,NA, 21.10,25.80,1008.80, 0.00, 0.00,31.00,
> > NA,821450)"
> > [6] "INSERT INTO OBS
> >
> (date,T_2M,TMAX_2M,TMIN_2M,TD_2M,PS,FF_10M,DD_10M,TOT_PRCP,CLCL,Station_NO)
> > VALUES (2011042912, 23.30,NA, 22.80,22.90,1001.60, 0.00, 0.00,24.00,
> > NA,821810)"
> > [7] "INSERT INTO OBS
> > ===
> >
>
> Please
>
> 1. reduce Allados to a smaller number of columns and rows. Say 10
> rows and 3 columns such that it still exhibits the problem and then
> show the result of dput:
>
> dput(smallDF)
>
> 2. provide the R code that you would use with smallDF
>
> 3. explain what the problem is and how that differs from what you expect.
>
> --
> Statistics & Software Consulting
> GKX Group, GKX Associates Inc.
> tel: 1-877-GKX-GROUP
> email: ggrothendieck at gmail.com
>
--
Abraço,
Nilza Barros
[[alternative HTML version deleted]]
__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Re: [R] Setting NA to blank
(mat <- matrix(c(1,2,3,NA),2)) mat[is.na(mat)] <- " " mat But if you have a numerical matrix it coverts the matrix to character. --- On Mon, 5/9/11, Dat Mai wrote: > From: Dat Mai > Subject: [R] Setting NA to blank > To: r-help@r-project.org > Received: Monday, May 9, 2011, 2:46 PM > Hey All, > > I have a matrix m, and I wish to set all the NA values to > blank. How would I > do so? > > -- > Best, > Dat Mai > PhD Rotation Student > Albert Einstein College of Medicine __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Create subsets of data
Hi, On Mon, May 9, 2011 at 9:40 AM, Pavan G wrote: > Hello All, > Let's say I have points on a x-y plane. x ranges from 0-2 and y from 0-2. > There are points in quadrants x[0:1]---y[0:1] and in x[1:2]y[1:2]. I > would like to get the mean and std of the points in the x[0:1]y[0:1] > quadrant alone. Is there a straight forward way to do it? > > I asked a similar question a few days ago regarding plotting a subset of > data using conditions. The solution was: > http://r.789695.n4.nabble.com/Conditional-plot-length-in-R-td3503855.html The solution to this question will also be similar, I guess ... you should take some time to figure out how indexing with (different types of) vectors works: http://cran.r-project.org/doc/manuals/R-intro.html#Index-vectors If your question doesn't have to do with selecting the appropriate elements of your data, are you asking how to take a "mean" or std.dev of the subset of points you know how to select? It's not clear what you mean by "mean" ... do you want the average value of x vs. avg. value of y ... or do you want the "centroid" of a set of points in each quadrant, or ... what? > Thank you, > Why-so-serious. A curious choice for a valediction ... -- Steve Lianoglou Graduate Student: Computational Systems Biology | Memorial Sloan-Kettering Cancer Center | Weill Medical College of Cornell University Contact Info: http://cbio.mskcc.org/~lianos/contact __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] How to alter circle size
All right then--I shall get bash away. Thanks a lot.
On Mon, May 9, 2011 at 2:55 PM, Deepayan Sarkar
wrote:
> On Mon, May 9, 2011 at 8:23 PM, Dat Mai wrote:
> > Thanks for the help! Though, when I do this, I get a message saying
> "Error
> > using packet 1 value where TRUE/FALSE." Would that have anything to do
> with
> > this set of code?
>
> It might. (As we don't know what you "did", we can't really say.)
>
> > On Sun, May 8, 2011 at 3:00 PM, Deepayan Sarkar <
> deepayan.sar...@gmail.com>
> > wrote:
> >>
> >> On Fri, May 6, 2011 at 10:21 PM, Dat Mai wrote:
> >> > Hello all,
> >> >
> >> > I'm trying to create a heatmap using 2 matrices I have: z and v. Both
> >> > matrices represent different correlations for the same independent
> >> > variables. The problem I have is that I wish to have the values from
> >> > matrix
> >> > z to be represented by color intensity while having the values from
> >> > matrix v
> >> > to be represented by circle size. I currently have the following in
> >> > front of
> >> > me and an unsure of what to add or change in order to achieve that
> goal.
> >> >
> >> > panel.corrgram.2 =
> >> > function(x, y, z, subscripts, at = pretty(z), scale = 0.8, ...)
> >> > {
> >> > require("grid", quietly = TRUE)
> >> > x <- as.numeric(x)[subscripts]
> >> > y <- as.numeric(y)[subscripts]
> >> > z <- as.numeric(z)[subscripts]
> >> > zcol <- level.colors(z, at = at, ...)
> >> > for (i in seq(along = z))
> >> > {
> >> >lims <- range(0, z[i])
> >> >tval <- 2 * base::pi * seq(from = lims[1], to = lims[2], by = 0.01)
> >> >grid.polygon(x = x[i] + .5 * scale * c(0, sin(tval)),
> >> > y = y[i] + .5 * scale * c(0, cos(tval)),
> >> > default.units = "native",
> >> > gp = gpar(fill = zcol[i]))
> >> >grid.circle(x = x[i], y = y[i], r = .5 * scale,
> >> > default.units = "native")
> >> > }
> >> > }
> >>
> >> Probably this modification
> >>
> >> panel.corrgram.2 <-
> >>function(x, y, z, v, subscripts, at = pretty(v), scale = 0.8, ...)
> >> {
> >>require("grid", quietly = TRUE)
> >>x <- as.numeric(x)[subscripts]
> >>y <- as.numeric(y)[subscripts]
> >>z <- as.numeric(z)[subscripts]
> >>zcol <- level.colors(v, at = at, ...)
> >>
> >>
> >>
> >>
> >> followed by
> >>
> >> levelplot(signif(z,3), v = v, panel = panel.corrgram.2, ...)
> >>
> >> will do it.
> >>
> >> -Deepayan
> >>
> >>
> >> >
> >> > k=levelplot(signif(z,3), scales = list(x = list(rot = 45)),
> >> > col.regions=col.sch, panel = panel.corrgram.2,
> >> > label = num.circ, xlab="", ylab="", main=paste(output,"receptor
> >> > response"))
> >> > print(k)
> >> >
> >> > --
> >> > Best,
> >> > Dat Mai
> >> > PhD Rotation Student
> >> > Albert Einstein College of Medicine
> >> >
> >> >[[alternative HTML version deleted]]
> >> >
> >> > __
> >> > R-help@r-project.org mailing list
> >> > https://stat.ethz.ch/mailman/listinfo/r-help
> >> > PLEASE do read the posting guide
> >> > http://www.R-project.org/posting-guide.html
> >> > and provide commented, minimal, self-contained, reproducible code.
>
--
Best,
Dat Mai
PhD Rotation Student
Albert Einstein College of Medicine
[[alternative HTML version deleted]]
__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Re: [R] How to alter circle size
On Mon, May 9, 2011 at 8:23 PM, Dat Mai wrote:
> Thanks for the help! Though, when I do this, I get a message saying "Error
> using packet 1 value where TRUE/FALSE." Would that have anything to do with
> this set of code?
It might. (As we don't know what you "did", we can't really say.)
> On Sun, May 8, 2011 at 3:00 PM, Deepayan Sarkar
> wrote:
>>
>> On Fri, May 6, 2011 at 10:21 PM, Dat Mai wrote:
>> > Hello all,
>> >
>> > I'm trying to create a heatmap using 2 matrices I have: z and v. Both
>> > matrices represent different correlations for the same independent
>> > variables. The problem I have is that I wish to have the values from
>> > matrix
>> > z to be represented by color intensity while having the values from
>> > matrix v
>> > to be represented by circle size. I currently have the following in
>> > front of
>> > me and an unsure of what to add or change in order to achieve that goal.
>> >
>> > panel.corrgram.2 =
>> > function(x, y, z, subscripts, at = pretty(z), scale = 0.8, ...)
>> > {
>> > require("grid", quietly = TRUE)
>> > x <- as.numeric(x)[subscripts]
>> > y <- as.numeric(y)[subscripts]
>> > z <- as.numeric(z)[subscripts]
>> > zcol <- level.colors(z, at = at, ...)
>> > for (i in seq(along = z))
>> > {
>> > lims <- range(0, z[i])
>> > tval <- 2 * base::pi * seq(from = lims[1], to = lims[2], by = 0.01)
>> > grid.polygon(x = x[i] + .5 * scale * c(0, sin(tval)),
>> > y = y[i] + .5 * scale * c(0, cos(tval)),
>> > default.units = "native",
>> > gp = gpar(fill = zcol[i]))
>> > grid.circle(x = x[i], y = y[i], r = .5 * scale,
>> > default.units = "native")
>> > }
>> > }
>>
>> Probably this modification
>>
>> panel.corrgram.2 <-
>> function(x, y, z, v, subscripts, at = pretty(v), scale = 0.8, ...)
>> {
>> require("grid", quietly = TRUE)
>> x <- as.numeric(x)[subscripts]
>> y <- as.numeric(y)[subscripts]
>> z <- as.numeric(z)[subscripts]
>> zcol <- level.colors(v, at = at, ...)
>>
>>
>>
>>
>> followed by
>>
>> levelplot(signif(z,3), v = v, panel = panel.corrgram.2, ...)
>>
>> will do it.
>>
>> -Deepayan
>>
>>
>> >
>> > k=levelplot(signif(z,3), scales = list(x = list(rot = 45)),
>> > col.regions=col.sch, panel = panel.corrgram.2,
>> > label = num.circ, xlab="", ylab="", main=paste(output,"receptor
>> > response"))
>> > print(k)
>> >
>> > --
>> > Best,
>> > Dat Mai
>> > PhD Rotation Student
>> > Albert Einstein College of Medicine
>> >
>> > [[alternative HTML version deleted]]
>> >
>> > __
>> > R-help@r-project.org mailing list
>> > https://stat.ethz.ch/mailman/listinfo/r-help
>> > PLEASE do read the posting guide
>> > http://www.R-project.org/posting-guide.html
>> > and provide commented, minimal, self-contained, reproducible code.
__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
[R] Setting NA to blank
Hey All, I have a matrix m, and I wish to set all the NA values to blank. How would I do so? -- Best, Dat Mai PhD Rotation Student Albert Einstein College of Medicine [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Vectorizing a function: what does it mean?
On 09/05/2011 11:57 AM, Ron Michael wrote: Dear all, I would really appreciate if somebody can help me to understand what does the phrase "Vectorize your function" mean? And what is the job of Vectorize() function in doing that? I have read many threads where experts suggest to Vectorize the function, which will speed up entire calculation (and more elegant ofcourse.) I used to think that vectorizing function means, to create a function such a way so that if input(s) are vector then this function will also return a vector output (without having any extra effort like use of 'for' loop etc.) Is this understanding correct? That's correct. Here I have tried 2 essentially similar functions: > fn1<- function(x,y,z) return(x+y+z) > fn2<- Vectorize(function(x,y,z) return(x+y+z), SIMPLIFY=TRUE) > fn1(1:3, 4:6,5) [1] 10 12 14 > fn2(1:3, 4:6,5) [1] 10 12 14 You see that, fn1() and fn2() is giving same answer (vectorized?) despite of the fact that fn1() is not wrapped within Vectorize() function. Therefore I want to know: what additional thing this Vectorize() function brings on the table? Addition is already vectorized, so Vectorize does nothing but slow down your function. In other cases it is more helpful. For example, if you wanted to compute the residual sum of squares from fitting a mean to a vector of data, you might write y <- rnorm(100) # some fake data RSS <- function(mu) sum( (y-mu)^2 ) That works only if mu is a scalar, but Vectorize(RSS) would work for a vector of mu values. Duncan Murdoch __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Vectorizing a function: what does it mean?
On 09/05/2011 1:31 PM, David Winsemius wrote:
On May 9, 2011, at 11:57 AM, Ron Michael wrote:
> Dear all, I would really appreciate if somebody can help me to
> understand what does the phrase "Vectorize your function" mean? And
> what is the job of Vectorize() function in doing that? I have read
> many threads where experts suggest to Vectorize the function, which
> will speed up entire calculation (and more elegant ofcourse.)
>
> I used to think that vectorizing function means, to create a
> function such a way so that if input(s) are vector then this
> function will also return a vector output (without having any extra
> effort like use of 'for' loop etc.) Is this understanding correct?
>
> Here I have tried 2 essentially similar functions:
>
>> fn1<- function(x,y,z) return(x+y+z)
>> fn2<- Vectorize(function(x,y,z) return(x+y+z), SIMPLIFY=TRUE)
>> fn1(1:3, 4:6,5)
> [1] 10 12 14
>> fn2(1:3, 4:6,5)
> [1] 10 12 14
>
>
> You see that, fn1() and fn2() is giving same answer (vectorized?)
> despite of the fact that fn1() is not wrapped within Vectorize()
> function. Therefore I want to know: what additional thing this
> Vectorize() function brings on the table?
That is because you used "+" which is "vectorized" to start with. Try
is with "sum" and you will not be as "happy"
> sum(a=1:3, b=4:6, cc=7:9)
[1] 45
It removed all your structure.
> Vsum<-function(...) {what<- list(...); lenlist<- length(what);
y<-matrix(unlist(what), ncol=lenlist); apply(y,1,sum)}
> Vsum(a=1:3, b=4:6, cc=7:9)
[1] 12 15 18
# Does not recycle as I might have expected, although it does recycle
> (Vsum( a=1:3, b=4:6, cc=7))
[1] 12 8 11
> (mapply(sum, a=1:3, b=4:6, cc=7:9))
# also works and recycles as expected:
[1] 12 15 18
> (mapply(sum, a=1:3, b=4:6, cc=7))
[1] 12 14 16
# but _not_ VSum<- Vectorize(sum) for reasons not clear to me behaves
the same as sum()
The problem with Vectorize(sum) is that Vectorize doesn`t see any
parameters to vectorize in sum(). It needs simple functions with
parameters like fn1, and it rewrites them to loop over the values of the
parameters.
Duncan Murdoch
__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
[R] Approximate name matching
Is there R software available for doing approximate matching of personal names? I have data about the same people produced by different organizations and the only matching key I have is the name. I know that commercial solutions exist, and I know I code code this from scratch, but I'd prefer to build on some existing free solution if it exists. Unfortunately, the names are not standardized, and there is also a certain level of error: Danny Williams (nickname) Dan Williams (nickname) Daniel Williams (nickname) Dan William (spelling error) D. Williams (initials) Daniel "Danny" Williams (formal + nickname) Dan P. Williams (includes middle initial) Williams, Daniel (different convention) William Daniel (wrong order or missing comma + misspelling) Is there any R software available to find likely matches, ideally with some estimate of accuracy of match? Levenshtein distance as implemented in agrep is a useful solution for some of these cases; I was wondering if there is something that covers more cases. For this particular application, I am not concerned with issues such as variant latinizations/transliterations (e.g. Tsung-Dao Lee ~ T.D. Lee ~ Li Zhengdao; Ghaddafi ~ Qaddhaffi), but of course if someone handles that as well Thanks, -s [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Round down to earliest hour or half hour
One way, assuming your timestamps are POSIXct format:
truncInterval <- function ( x, dx=as.difftime(1,units="days") ) {
xn <- as.numeric( x )
result <- xn - xn %% as.numeric( dx, units="secs" )
class( result ) <- 'POSIXct'
result
}
truncInterval( as.POSIXct(c("2011-04-28 09:20:00", "2011-04-28 09:40:00")),
as.difftime(30,units="mins") )
This may not work well if the timestamp granularity is more fine than one
second.
---
Jeff Newmiller The . . Go Live...
DCN: Basics: ##.#. ##.#. Live Go...
Live: OO#.. Dead: OO#.. Playing
Research Engineer (Solar/Batteries O.O#. #.O#. with
/Software/Embedded Controllers) .OO#. .OO#. rocks...1k
---
Sent from my phone. Please excuse my brevity.
Schatzi wrote:
I have times and would like to round down to the earliest 30 minute increment.
For instance, a time of 2011-04-28 09:02:00 (the as.numeric value = 1303999320)
I would like it to be rounded down to: 2011-04-28 09:00:00 (the as.numeric
value = 1303999200) Any ideas of how to do this? - In theory, practice and
theory are the same. In practice, they are not - Albert Einstein -- View this
message in context:
http://r.789695.n4.nabble.com/Round-down-to-earliest-hour-or-half-hour-tp3509374p3509374.html
Sent from the R help mailing list archive at
Nabble.com._
R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
[[alternative HTML version deleted]]
__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Re: [R] Time Series
On Mon, May 9, 2011 at 10:20 AM, Nicole Gross-Camp wrote: > I have what I hope is a simple question - is it possible to do time series > analysis on a small data set specifically only four data points? > > > > I have collected human threat data (mean number of threats per kilometre > walked/ survey) every 3 months in eight different sites (four with an > experimental element and four control sites). I am trying to determine the > best way to determine if there is a trend in the data though from what I've > seen of TSA, our data set is too small. I did a simple paired t-test on the > first and average of following three surveys that shows no significant > difference but it of course ignores the detail of the latter three surveys. > > > > I am not sure how to organize the data for importation into R. I've looked > at Crawley and one of Zuur publications but the TS data they work with is > much longer term and not over several (independent) sites. > > > > Any advice, help, or direction is much appreciated! > This i panel data where you have 8 time series, not one time series, right? You could try a gls model with an AR1 correlation error structure for each of the 8 series. See the analysis of the Owl data set in Zuur. -- Statistics & Software Consulting GKX Group, GKX Associates Inc. tel: 1-877-GKX-GROUP email: ggrothendieck at gmail.com __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] arima residuals
Hi I have fitted an arima model to a monthly series of length 113. I have use fit <- arima(x.ts, order = c(1,0,0),seas = list(order = c(1,2,1),12, method = "CSS") I'm a little confused because the series of residual has the first 46 values equal to 0. From there the residuals are approximately while noise, numbers have a mean close to 0 and a variance value. What could be causing these results? -- Luis [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] Fortran Symbol Name not in Load Table
I am trying to call a FORTRAN subroutine from R. is.loaded is turning out to
be TRUE. However when I run my .Fortran command I get the following error:
Error in .Fortran("VALUEAHROPTIMIZE", as.double(ahrArray),
as.double(kwArray), :
Fortran symbol name "valueahroptimize" not in load table
I have given the FORTRAN declaration below:
subroutine VALUEAHROPTIMIZE(AHR,&
KW,&
min_IHR_delta, &
max_AHR_error, &
AHR_out, & !! Output AHE array
IHR_out, & !! Output IHR array
Errors_out)
! Expose subroutine my_function to users of this DLL
!DEC$ ATTRIBUTES
DLLEXPORT,C,REFERENCE,ALIAS:'VALUEAHROPTIMIZE_'::VALUEAHROPTIMIZE
! Body of my_function
Implicit None
Integer *4 IERR, iSum
DOUBLE PRECISION min_IHR_delta, max_AHR_error
logical switch_AHR_tuner
character * 512 AHR_tuner_FilePath
!!DOUBLE PRECISION AHR(500), kW(500) !! Initial Array for reading
Namelist
DOUBLE PRECISION AHR(*), kW(*) !! Initial Array for reading Namelist
DOUBLE PRECISION AHR_out(*), IHR_out(*)
integer Errors_out(*)
The R code I tried using is given below:
ahrArray <- runif(147)
kwArray <- runif(147)
outputAHR <- c(rep(0,11*11))
outputIHR <- c(rep(0,11*11))
outputError <- c(rep(NA,11))
dyn.load("my_function.dll")
is.loaded("VALUEAHROPTIMIZE")
[1] TRUE
> .Fortran("VALUEAHROPTIMIZE",
as.double(ahrArray),
as.double(kwArray),
as.double(0.0005),
as.double(5),
as.double(outputAHR),
as.double(outputIHR),
as.integer(outputError))
Can someone please help me with how to fix this issue? Thank you.
Ravi
--
View this message in context:
http://r.789695.n4.nabble.com/Fortran-Symbol-Name-not-in-Load-Table-tp3509852p3509852.html
Sent from the R help mailing list archive at Nabble.com.
__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Re: [R] Vectorizing a function: what does it mean?
On May 9, 2011, at 11:57 AM, Ron Michael wrote:
Dear all, I would really appreciate if somebody can help me to
understand what does the phrase "Vectorize your function" mean? And
what is the job of Vectorize() function in doing that? I have read
many threads where experts suggest to Vectorize the function, which
will speed up entire calculation (and more elegant ofcourse.)
I used to think that vectorizing function means, to create a
function such a way so that if input(s) are vector then this
function will also return a vector output (without having any extra
effort like use of 'for' loop etc.) Is this understanding correct?
Here I have tried 2 essentially similar functions:
fn1 <- function(x,y,z) return(x+y+z)
fn2 <- Vectorize(function(x,y,z) return(x+y+z), SIMPLIFY=TRUE)
fn1(1:3, 4:6,5)
[1] 10 12 14
fn2(1:3, 4:6,5)
[1] 10 12 14
You see that, fn1() and fn2() is giving same answer (vectorized?)
despite of the fact that fn1() is not wrapped within Vectorize()
function. Therefore I want to know: what additional thing this
Vectorize() function brings on the table?
That is because you used "+" which is "vectorized" to start with. Try
is with "sum" and you will not be as "happy"
> sum(a=1:3, b=4:6, cc=7:9)
[1] 45
It removed all your structure.
> Vsum <-function(...) {what <- list(...); lenlist <- length(what);
y<-matrix(unlist(what), ncol=lenlist); apply(y,1,sum)}
> Vsum(a=1:3, b=4:6, cc=7:9)
[1] 12 15 18
# Does not recycle as I might have expected, although it does recycle
> (Vsum( a=1:3, b=4:6, cc=7))
[1] 12 8 11
> (mapply(sum, a=1:3, b=4:6, cc=7:9))
# also works and recycles as expected:
[1] 12 15 18
> (mapply(sum, a=1:3, b=4:6, cc=7))
[1] 12 14 16
# but _not_ VSum <- Vectorize(sum) for reasons not clear to me behaves
the same as sum()
Thanks for your time.
__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
David Winsemius, MD
West Hartford, CT
__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Re: [R] Using NULL to my data?
On Mon, May 9, 2011 at 12:59 PM, Nilza BARROS wrote: > Hi, Thanks for your attentio. > > I have the data frame below: > >> head(Alldados) > Station_NO date1 T_2M TMAX_2M TMIN_2M TD_2M PS FF_10M DD_10M > 1 820420 110429/1200 22.5 NULL 22.4 22.2 NULL 0 0 > 2 820980 110429/1200 26.9 NULL 23.4 24.1 1010.2 2.91 360 > 3 821130 110429/1200 24.3 NULL 23.3 23.7 NULL 1.94 230 > 4 821410 110429/1200 24.4 NULL 23.7 24.2 1011.8 2.91 270 > 5 821450 110429/1200 28.2 NULL 21.1 25.8 1008.8 0 0 > 6 821810 110429/1200 23.3 NULL 22.8 22.9 1001.6 0 0 > TOT_PRCP CLCL date2 > 1 84.00 NULL 2011042912 > 2 2.00 NULL 2011042912 > 3 3.00 NULL 2011042912 > 4 12.00 NULL 2011042912 > 5 6.00 NULL 2011042912 > 6 38.00 NULL 2011042912 > > Now each line will feed my database. So I need to format each line like > below: > > === > [1] "INSERT INTO OBS > (date,T_2M,TMAX_2M,TMIN_2M,TD_2M,PS,FF_10M,DD_10M,TOT_PRCP,CLCL,Station_NO) > VALUES (2011042912, 22.50, NA, 22.40,22.20, NA, 0.00, 0.00,36.00, > NA,820420)" > [2] "INSERT INTO OBS > (date,T_2M,TMAX_2M,TMIN_2M,TD_2M,PS,FF_10M,DD_10M,TOT_PRCP,CLCL,Station_NO) > VALUES (2011042912, 26.90, NA, 23.40,24.10,1010.20, 2.91,360.00,16.00, > NA,820980)" > [3] "INSERT INTO OBS > (date,T_2M,TMAX_2M,TMIN_2M,TD_2M,PS,FF_10M,DD_10M,TOT_PRCP,CLCL,Station_NO) > VALUES (2011042912, 24.30, NA, 23.30,23.70, NA, 1.94,230.00,19.00, > NA,821130)" > [4] "INSERT INTO OBS > (date,T_2M,TMAX_2M,TMIN_2M,TD_2M,PS,FF_10M,DD_10M,TOT_PRCP,CLCL,Station_NO) > VALUES (2011042912, 24.40, NA, 23.70,24.20,1011.80, 2.91,270.00,12.00, > NA,821410)" > [5] "INSERT INTO OBS > (date,T_2M,TMAX_2M,TMIN_2M,TD_2M,PS,FF_10M,DD_10M,TOT_PRCP,CLCL,Station_NO) > VALUES (2011042912, 28.20, NA, 21.10,25.80,1008.80, 0.00, 0.00,31.00, > NA,821450)" > [6] "INSERT INTO OBS > (date,T_2M,TMAX_2M,TMIN_2M,TD_2M,PS,FF_10M,DD_10M,TOT_PRCP,CLCL,Station_NO) > VALUES (2011042912, 23.30, NA, 22.80,22.90,1001.60, 0.00, 0.00,24.00, > NA,821810)" > [7] "INSERT INTO OBS > === > Please 1. reduce Allados to a smaller number of columns and rows. Say 10 rows and 3 columns such that it still exhibits the problem and then show the result of dput: dput(smallDF) 2. provide the R code that you would use with smallDF 3. explain what the problem is and how that differs from what you expect. -- Statistics & Software Consulting GKX Group, GKX Associates Inc. tel: 1-877-GKX-GROUP email: ggrothendieck at gmail.com __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Using NULL to my data?
Hi, Thanks for your attentio.
I have the data frame below:
> head(Alldados)
Station_NO date1 T_2M TMAX_2M TMIN_2M TD_2M PS FF_10M DD_10M
1 820420 110429/1200 22.5NULL22.4 22.2 NULL 0 0
2 820980 110429/1200 26.9NULL23.4 24.1 1010.2 2.91360
3 821130 110429/1200 24.3NULL23.3 23.7 NULL 1.94230
4 821410 110429/1200 24.4NULL23.7 24.2 1011.8 2.91270
5 821450 110429/1200 28.2NULL21.1 25.8 1008.8 0 0
6 821810 110429/1200 23.3NULL22.8 22.9 1001.6 0 0
TOT_PRCP CLCL date2
184.00 NULL 2011042912
2 2.00 NULL 2011042912
3 3.00 NULL 2011042912
412.00 NULL 2011042912
5 6.00 NULL 2011042912
638.00 NULL 2011042912
Now each line will feed my database. So I need to format each line like
below:
===
[1] "INSERT INTO OBS
(date,T_2M,TMAX_2M,TMIN_2M,TD_2M,PS,FF_10M,DD_10M,TOT_PRCP,CLCL,Station_NO)
VALUES (2011042912, 22.50,NA, 22.40,22.20, NA, 0.00, 0.00,36.00,
NA,820420)"
[2] "INSERT INTO OBS
(date,T_2M,TMAX_2M,TMIN_2M,TD_2M,PS,FF_10M,DD_10M,TOT_PRCP,CLCL,Station_NO)
VALUES (2011042912, 26.90,NA, 23.40,24.10,1010.20, 2.91,360.00,16.00,
NA,820980)"
[3] "INSERT INTO OBS
(date,T_2M,TMAX_2M,TMIN_2M,TD_2M,PS,FF_10M,DD_10M,TOT_PRCP,CLCL,Station_NO)
VALUES (2011042912, 24.30,NA, 23.30,23.70, NA, 1.94,230.00,19.00,
NA,821130)"
[4] "INSERT INTO OBS
(date,T_2M,TMAX_2M,TMIN_2M,TD_2M,PS,FF_10M,DD_10M,TOT_PRCP,CLCL,Station_NO)
VALUES (2011042912, 24.40,NA, 23.70,24.20,1011.80, 2.91,270.00,12.00,
NA,821410)"
[5] "INSERT INTO OBS
(date,T_2M,TMAX_2M,TMIN_2M,TD_2M,PS,FF_10M,DD_10M,TOT_PRCP,CLCL,Station_NO)
VALUES (2011042912, 28.20,NA, 21.10,25.80,1008.80, 0.00, 0.00,31.00,
NA,821450)"
[6] "INSERT INTO OBS
(date,T_2M,TMAX_2M,TMIN_2M,TD_2M,PS,FF_10M,DD_10M,TOT_PRCP,CLCL,Station_NO)
VALUES (2011042912, 23.30,NA, 22.80,22.90,1001.60, 0.00, 0.00,24.00,
NA,821810)"
[7] "INSERT INTO OBS
===
I hope it helps.
Best Regards,
Nilza
On Mon, May 9, 2011 at 1:47 PM, Gabor Grothendieck
wrote:
> You certainly can't assign a character string into a numeric column.
> There is no reason to expect that to work.
>
> Can you provide some clarity on what the problem is in terms of a very
> small self contained example explaining what you get and what you
> expected to get.
>
> Regards.
>
> On Mon, May 9, 2011 at 12:40 PM, Nilza BARROS
> wrote:
> > Dear Ruser,
> >
> > Thank for your help.
> > I've just tried the command below and it works
> > Alldados[is.na(Alldados)]<-"NULL"
> >
> > But I am facing other problem, since I need to format my data before
> feeding
> > my database.
> > I am using the command below:
> >
> > with(Alldados,sprintf("INSERT INTO OBS
> >
> (date,T_2M,TMAX_2M,TMIN_2M,TD_2M,PS,FF_10M,DD_10M,TOT_PRCP,CLCL,Station_NO)
> > VALUES (%s, %5.2f, %5.2f, %5.2f,%5.2f,%5.2f,%5.2f,%5.2f,%5.2f,%5.2f,%s)",
> >
> >
> date2,T_2M,TMAX_2M,TMIN_2M,TD_2M,PS,FF_10M,DD_10M,TOT_PRCP,CLCL,Station_NO))
> >
> > But it is not working anymore. Because now the same field can be numeric
> or
> > character.
> > How can I use the format command above the allow it.
> >
> > I really appreciate any help.
> > Nilza
> >
> >
> >
> >
> >
> > On Mon, May 9, 2011 at 12:55 PM, David Winsemius >wrote:
> >
> >>
> >> On May 9, 2011, at 10:07 AM, Nilza BARROS wrote:
> >>
> >> Dear R users,
> >>>
> >>> I am reading data from a file where there are some missing that are
> >>> represented by -.00.
> >>> I am using the command below.
> >>> =My original data ===
> >>>
> >>> PARM = TMPC;T12X;T12N;DWPC;PALT;SKNT;DRCT;P24M;CLCL
> >>>
> >>
> >> snipped
> >>
> >>
> >> But I need to feed my database. These missings should be represented by
> >>> NULL.
> >>> I mean, all "NA" should be replaced by "NULL" in my database.
> >>>
> >>
> >> Do you mean a string that is spelled "NULL"
> >>
> >> If so, try:
> >>
> >> dfrm[is.na(dfrm)] <- "NULL"
> >>
> >>
> >> I am trying the command below to pick up the rows and columns with NA
> but I
> >>> don't know how to fill the original data :
> >>>
> >>> which(is.na(Alldados),arr.ind=TRUE)
> >>>
> >>> But I don't know how to replace each NA with NULL. I tried using
> as.null
> >>> but
> >>> NA is not replace at all.
> >>>
> >>
> >> If you set a column of a data.frame to NULL , it will erase it.
> >>
> >>
> >>
> >>> I hope someone could help me.
> >>>
> >>> Best Wishes,
> >>> Nilza Barros
> >>>
> >>>
> >> David Winsemius, MD
> >> West Hartford, CT
> >>
> >>
> >
> >
> > --
> > Abraço,
> > Nilza Barros
> >
> >[[alternative HTML version deleted]]
> >
> >
> > __
> > R-help@r-project.org mailing list
> > https://stat.ethz.ch/mailman/listinfo/r-help
> > PLEASE do read the posting guide
> http://www.R-project.org/posting-guide.html
> > and provide commented, minimal, self-contained, reproducible
Re: [R] Vermunt's LEM in R
What is L_square? Is it Likelihood ratio/deviance statistic which is reported by poLCA? The predcell component contains observed and expected, isn't it easy to get the residuals? If you want the logit/logistic model, glm or lrm (rms) can do the job. It is unrealistic to expect different software report the exact result, though most of them report the most important and basic statistics. On 10 May 2011 00:12, David Joubert wrote: > > > Basically I do LCA, followed by some kind of analysis intended to validate > the solutions. For example, I would create latent class solutions for each > gender based on four dichotomic indicators of psychosis. Next, I would look > at the interaction of current psychiatric status (the classes) and past > psychiatric diagnosis to predict institutional treatment use (logit or > logistic models). poLCA is a little limited for this purpose; I would have to > use it in combination with some other package. For example, it doesn't > provide residuals for the indicators, or the Cressie-Read statistic. > > David Joubert > > > Date: Fri, 6 May 2011 09:56:05 +0200 > Subject: Re: [R] Vermunt's LEM in R > From: i.vis...@uva.nl > To: ronggui.hu...@gmail.com > CC: jo...@hotmail.com; r-help@r-project.org > > poLCA is an option, as is randomLCA, flexmix, and depmixS4, and there are > likely to be more > What specific models are you interested in? > Best, Ingmar > > On Fri, May 6, 2011 at 6:13 AM, Wincent wrote: > > I guess LEM is a software for latent class analysis. If so, you may > > want to have a look at poLCA package. > > > > Regards > > Ronggui > > > > On 5 May 2011 23:34, David Joubert wrote: > >> > >> Hello- > >> > >> Does anyone know of packages that could emulate what J. Vermunt's LEM does ? >> What is the closest relative in R ? > >> I use both R and LEM but have trouble transforming my multiway tables in R >> into a .dat file compatible with LEM. > >> > >> Thanks, > >> > >> David Joubert > >> > >> [[alternative HTML version deleted]] > >> > >> __ > >> R-help@r-project.org mailing list > >> https://stat.ethz.ch/mailman/listinfo/r-help > >> PLEASE do read the posting guide http://www.R-project.org/posting-guide.html > >> and provide commented, minimal, self-contained, reproducible code. > >> > > > > > > > > -- > > Wincent Ronggui HUANG > > Sociology Department of Fudan University > > PhD of City University of Hong Kong > > http://asrr.r-forge.r-project.org/rghuang.html > > > > __ > > R-help@r-project.org mailing list > > https://stat.ethz.ch/mailman/listinfo/r-help > > PLEASE do read the posting guide http://www.R-project.org/posting-guide.html > > and provide commented, minimal, self-contained, reproducible code. > > > > [[alternative HTML version deleted]] > > __ > R-help@r-project.org mailing list > https://stat.ethz.ch/mailman/listinfo/r-help > PLEASE do read the posting guide http://www.R-project.org/posting-guide.html > and provide commented, minimal, self-contained, reproducible code. > -- Wincent Ronggui HUANG Sociology Department of Fudan University PhD of City University of Hong Kong http://asrr.r-forge.r-project.org/rghuang.html __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Using NULL to my data?
You certainly can't assign a character string into a numeric column.
There is no reason to expect that to work.
Can you provide some clarity on what the problem is in terms of a very
small self contained example explaining what you get and what you
expected to get.
Regards.
On Mon, May 9, 2011 at 12:40 PM, Nilza BARROS wrote:
> Dear Ruser,
>
> Thank for your help.
> I've just tried the command below and it works
> Alldados[is.na(Alldados)]<-"NULL"
>
> But I am facing other problem, since I need to format my data before feeding
> my database.
> I am using the command below:
>
> with(Alldados,sprintf("INSERT INTO OBS
> (date,T_2M,TMAX_2M,TMIN_2M,TD_2M,PS,FF_10M,DD_10M,TOT_PRCP,CLCL,Station_NO)
> VALUES (%s, %5.2f, %5.2f, %5.2f,%5.2f,%5.2f,%5.2f,%5.2f,%5.2f,%5.2f,%s)",
>
> date2,T_2M,TMAX_2M,TMIN_2M,TD_2M,PS,FF_10M,DD_10M,TOT_PRCP,CLCL,Station_NO))
>
> But it is not working anymore. Because now the same field can be numeric or
> character.
> How can I use the format command above the allow it.
>
> I really appreciate any help.
> Nilza
>
>
>
>
>
> On Mon, May 9, 2011 at 12:55 PM, David Winsemius
> wrote:
>
>>
>> On May 9, 2011, at 10:07 AM, Nilza BARROS wrote:
>>
>> Dear R users,
>>>
>>> I am reading data from a file where there are some missing that are
>>> represented by -.00.
>>> I am using the command below.
>>> =My original data ===
>>>
>>> PARM = TMPC;T12X;T12N;DWPC;PALT;SKNT;DRCT;P24M;CLCL
>>>
>>
>> snipped
>>
>>
>> But I need to feed my database. These missings should be represented by
>>> NULL.
>>> I mean, all "NA" should be replaced by "NULL" in my database.
>>>
>>
>> Do you mean a string that is spelled "NULL"
>>
>> If so, try:
>>
>> dfrm[is.na(dfrm)] <- "NULL"
>>
>>
>> I am trying the command below to pick up the rows and columns with NA but I
>>> don't know how to fill the original data :
>>>
>>> which(is.na(Alldados),arr.ind=TRUE)
>>>
>>> But I don't know how to replace each NA with NULL. I tried using as.null
>>> but
>>> NA is not replace at all.
>>>
>>
>> If you set a column of a data.frame to NULL , it will erase it.
>>
>>
>>
>>> I hope someone could help me.
>>>
>>> Best Wishes,
>>> Nilza Barros
>>>
>>>
>> David Winsemius, MD
>> West Hartford, CT
>>
>>
>
>
> --
> Abraço,
> Nilza Barros
>
> [[alternative HTML version deleted]]
>
>
> __
> R-help@r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.
>
>
--
Statistics & Software Consulting
GKX Group, GKX Associates Inc.
tel: 1-877-GKX-GROUP
email: ggrothendieck at gmail.com
__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Re: [R] Using NULL to my data?
Dear Ruser,
Thank for your help.
I've just tried the command below and it works
Alldados[is.na(Alldados)]<-"NULL"
But I am facing other problem, since I need to format my data before feeding
my database.
I am using the command below:
with(Alldados,sprintf("INSERT INTO OBS
(date,T_2M,TMAX_2M,TMIN_2M,TD_2M,PS,FF_10M,DD_10M,TOT_PRCP,CLCL,Station_NO)
VALUES (%s, %5.2f, %5.2f, %5.2f,%5.2f,%5.2f,%5.2f,%5.2f,%5.2f,%5.2f,%s)",
date2,T_2M,TMAX_2M,TMIN_2M,TD_2M,PS,FF_10M,DD_10M,TOT_PRCP,CLCL,Station_NO))
But it is not working anymore. Because now the same field can be numeric or
character.
How can I use the format command above the allow it.
I really appreciate any help.
Nilza
On Mon, May 9, 2011 at 12:55 PM, David Winsemius wrote:
>
> On May 9, 2011, at 10:07 AM, Nilza BARROS wrote:
>
> Dear R users,
>>
>> I am reading data from a file where there are some missing that are
>> represented by -.00.
>> I am using the command below.
>> =My original data ===
>>
>> PARM = TMPC;T12X;T12N;DWPC;PALT;SKNT;DRCT;P24M;CLCL
>>
>
> snipped
>
>
> But I need to feed my database. These missings should be represented by
>> NULL.
>> I mean, all "NA" should be replaced by "NULL" in my database.
>>
>
> Do you mean a string that is spelled "NULL"
>
> If so, try:
>
> dfrm[is.na(dfrm)] <- "NULL"
>
>
> I am trying the command below to pick up the rows and columns with NA but I
>> don't know how to fill the original data :
>>
>> which(is.na(Alldados),arr.ind=TRUE)
>>
>> But I don't know how to replace each NA with NULL. I tried using as.null
>> but
>> NA is not replace at all.
>>
>
> If you set a column of a data.frame to NULL , it will erase it.
>
>
>
>> I hope someone could help me.
>>
>> Best Wishes,
>> Nilza Barros
>>
>>
> David Winsemius, MD
> West Hartford, CT
>
>
--
Abraço,
Nilza Barros
[[alternative HTML version deleted]]
__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
[R] Vectorizing a function: what does it mean?
Dear all, I would really appreciate if somebody can help me to understand what does the phrase "Vectorize your function" mean? And what is the job of Vectorize() function in doing that? I have read many threads where experts suggest to Vectorize the function, which will speed up entire calculation (and more elegant ofcourse.) I used to think that vectorizing function means, to create a function such a way so that if input(s) are vector then this function will also return a vector output (without having any extra effort like use of 'for' loop etc.) Is this understanding correct? Here I have tried 2 essentially similar functions: > fn1 <- function(x,y,z) return(x+y+z) > fn2 <- Vectorize(function(x,y,z) return(x+y+z), SIMPLIFY=TRUE) > fn1(1:3, 4:6,5) [1] 10 12 14 > fn2(1:3, 4:6,5) [1] 10 12 14 You see that, fn1() and fn2() is giving same answer (vectorized?) despite of the fact that fn1() is not wrapped within Vectorize() function. Therefore I want to know: what additional thing this Vectorize() function brings on the table? Thanks for your time. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Vermunt's LEM in R
Basically I do LCA, followed by some kind of analysis intended to validate the solutions. For example, I would create latent class solutions for each gender based on four dichotomic indicators of psychosis. Next, I would look at the interaction of current psychiatric status (the classes) and past psychiatric diagnosis to predict institutional treatment use (logit or logistic models). poLCA is a little limited for this purpose; I would have to use it in combination with some other package. For example, it doesn't provide residuals for the indicators, or the Cressie-Read statistic. David Joubert Date: Fri, 6 May 2011 09:56:05 +0200 Subject: Re: [R] Vermunt's LEM in R From: i.vis...@uva.nl To: ronggui.hu...@gmail.com CC: jo...@hotmail.com; r-help@r-project.org poLCA is an option, as is randomLCA, flexmix, and depmixS4, and there are likely to be more What specific models are you interested in? Best, Ingmar On Fri, May 6, 2011 at 6:13 AM, Wincent wrote: I guess LEM is a software for latent class analysis. If so, you may want to have a look at poLCA package. Regards Ronggui On 5 May 2011 23:34, David Joubert wrote: > > Hello- > > Does anyone know of packages that could emulate what J. Vermunt's LEM does ? > What is the closest relative in R ? > I use both R and LEM but have trouble transforming my multiway tables in R > into a .dat file compatible with LEM. > > Thanks, > > David Joubert > >[[alternative HTML version deleted]] > > __ > R-help@r-project.org mailing list > https://stat.ethz.ch/mailman/listinfo/r-help > PLEASE do read the posting guide http://www.R-project.org/posting-guide.html > and provide commented, minimal, self-contained, reproducible code. > -- Wincent Ronggui HUANG Sociology Department of Fudan University PhD of City University of Hong Kong http://asrr.r-forge.r-project.org/rghuang.html __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Vermunt's LEM in R
Sure, sorry for not clarifying from the beginning. LEM is a rather powerful software for conducting general loglinear analysis, including latent class, logit, latent Markov, Event History models, etc. It's very polyvalent. Link to the software and document is at http://www.tilburguniversity.edu/nl/over-tilburg-university/schools/socialsciences/organisatie/departementen/mto/software2.html. Since I use R for other types of analyses, it would be good to have the equivalent in R without having to go back and forth between LEM and R. The packages that do LCA in R miss several important features (L-square statistic, Entropy, Cressie-Read, residuals, etc.). Thanks, David Joubert > Date: Fri, 6 May 2011 09:37:02 +1000 > From: a.robin...@ms.unimelb.edu.au > To: jo...@hotmail.com > CC: r-help@r-project.org > Subject: Re: [R] Vermunt's LEM in R > > Hi David, > > you might have more luck with your request if you tell us what > Vermunt's LEM *does*, and provided some links to introductory reading > material ... > > Cheers > > Andrew > > On Thu, May 05, 2011 at 03:34:02PM +, David Joubert wrote: > > > > Hello- > > > > Does anyone know of packages that could emulate what J. Vermunt's LEM does > > ? What is the closest relative in R ? > > I use both R and LEM but have trouble transforming my multiway tables in R > > into a .dat file compatible with LEM. > > > > Thanks, > > > > David Joubert > > > > [[alternative HTML version deleted]] > > > > __ > > R-help@r-project.org mailing list > > https://stat.ethz.ch/mailman/listinfo/r-help > > PLEASE do read the posting guide http://www.R-project.org/posting-guide.html > > and provide commented, minimal, self-contained, reproducible code. > > -- > Andrew Robinson > Program Manager, ACERA > Department of Mathematics and StatisticsTel: +61-3-8344-6410 > University of Melbourne, VIC 3010 Australia (prefer email) > http://www.ms.unimelb.edu.au/~andrewpr Fax: +61-3-8344-4599 > http://www.acera.unimelb.edu.au/ > > Forest Analytics with R (Springer, 2011) > http://www.ms.unimelb.edu.au/FAwR/ > Introduction to Scientific Programming and Simulation using R (CRC, 2009): > http://www.ms.unimelb.edu.au/spuRs/ [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Using NULL to my data?
On May 9, 2011, at 10:07 AM, Nilza BARROS wrote: Dear R users, I am reading data from a file where there are some missing that are represented by -.00. I am using the command below. =My original data === PARM = TMPC;T12X;T12N;DWPC;PALT;SKNT;DRCT;P24M;CLCL snipped But I need to feed my database. These missings should be represented by NULL. I mean, all "NA" should be replaced by "NULL" in my database. Do you mean a string that is spelled "NULL" If so, try: dfrm[is.na(dfrm)] <- "NULL" I am trying the command below to pick up the rows and columns with NA but I don't know how to fill the original data : which(is.na(Alldados),arr.ind=TRUE) But I don't know how to replace each NA with NULL. I tried using as.null but NA is not replace at all. If you set a column of a data.frame to NULL , it will erase it. I hope someone could help me. Best Wishes, Nilza Barros David Winsemius, MD West Hartford, CT __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Pretty printing numbers
On 2011-05-08 16:41, Worik R wrote: Friends I am trying to format a number to a string so 2189.745 goes to "2,189.35" and 309283.929 goes to "309,283.93" I have tried to use formatC(X, big.mark=",",drop0trailing=FALSE, format="f") but it does not get the number of decimals correct. Specifying digits does not work as that is significant digits. I could use a switch statement switching on the size of the number to be formated to set the digits parameter but that is complex and leaves me insecure that thre may be other problems I have not uncovered. I see that you've had the solution you seek in terms of round(), but what exactly is wrong with the 'digits' argument? It works for me in the cases you cite. (Note that format = "f" is handled differently from other formats, according to ?formatC.) Peter Ehlers Is there a simple way of using library functions to insert big.marks and get the number of trailing digits correct? Perhaps some way of using sprintf? cheers Worik [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Round down to earliest hour or half hour
I would use package chron and trunc()
One example from the help of trunc.times (modified):
lirary(chron)
tt <- times(c("12:13:14", "15:46:17"))
trunc(tt, times("00:30:00"))
HTH
Jannis
--- Schatzi schrieb am Mo, 9.5.2011:
> Von: Schatzi
> Betreff: [R] Round down to earliest hour or half hour
> An: r-help@r-project.org
> Datum: Montag, 9. Mai, 2011 14:06 Uhr
> I have times and would like to round
> down to the earliest 30 minute
> increment. For instance, a time of
> 2011-04-28 09:02:00
> (the as.numeric value = 1303999320)
> I would like it to be rounded down to:
> 2011-04-28 09:00:00
> (the as.numeric value = 1303999200)
>
> Any ideas of how to do this?
>
> -
> In theory, practice and theory are the same. In practice,
> they are not - Albert Einstein
> --
> View this message in context:
> http://r.789695.n4.nabble.com/Round-down-to-earliest-hour-or-half-hour-tp3509374p3509374.html
> Sent from the R help mailing list archive at Nabble.com.
>
> __
> R-help@r-project.org
> mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained,
> reproducible code.
>
__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
[R] Odp: Using NULL to my data?
Hi
r-help-boun...@r-project.org napsal dne 09.05.2011 16:07:27:
> Nilza BARROS
> Odeslal: r-help-boun...@r-project.org
>
> 09.05.2011 16:07
>
>
> Dear R users,
>
> I am reading data from a file where there are some missing that are
> represented by -.00.
> I am using the command below.
> =My original data ===
>
> PARM = TMPC;T12X;T12N;DWPC;PALT;SKNT;DRCT;P24M;CLCL
>
>
> STNYYMMDD/HHMM TMPC T12X T12N DWPC PALT
> SKNT
> DRCT P24M CLCL
> 820420110429/1200 22.50 -.0022.4022.20 -.00
> 0.00
> 0.0084.00 4.00
> 820980110429/1200 26.90 -.0023.4024.10 1010.20
> 2.91
> 360.00 2.00 6.00
> 821130110429/1200 24.30 -.0023.3023.70 -.00
> 1.94
> 230.00 3.00 4.00
> 821410110429/1200 24.40 -.0023.7024.20 1011.80
> 2.91
> ===
>
> dados<-read.table
> ("2011042912_teste.dat",sep='',fill=TRUE,na.strings="-.00",skip=4)
> head(dados)
> V1 V2 V3 V4 V5 V6 V7 V8 group
> 1 820420 110429/1200 22.5 NA 22.4 22.2 NA 0.00 1
> 2 0 84.00 4.0 NA NA NA NA NA 1
> 3 820980 110429/1200 26.9 NA 23.4 24.1 1010.2 2.91 2
> 43602.00 6.0 NA NA NA NA NA 2
> 5 821130 110429/1200 24.3 NA 23.3 23.7 NA 1.94 3
> 62303.00 4.0 NA NA NA NA NA 3
> =
> After some procedures a have the data as below:
> > head(Alldados)
>
>
> Station_NO date1 T_2M TMAX_2M TMIN_2M TD_2M PS FF_10M DD_10M
> 1 820420 110429/1200 22.5 NA22.4 22.2 NA 0.00 0
> 2 820980 110429/1200 26.9 NA23.4 24.1 1010.2 2.91360
> 3 821130 110429/1200 24.3 NA23.3 23.7 NA 1.94230
> 4 821410 110429/1200 24.4 NA23.7 24.2 1011.8 2.91270
> 5 821450 110429/1200 28.2 NA21.1 25.8 1008.8 0.00 0
> 6 821810 110429/1200 23.3 NA22.8 22.9 1001.6 0.00 0
> TOT_PRCP CLCL date2
> 184.00 NA 2011042912
> 2 2.00 NA 2011042912
> 3 3.00 NA 2011042912
> 412.00 NA 2011042912
> 5 6.00 NA 2011042912
> 638.00 NA 2011042912
>
> But I need to feed my database. These missings should be represented by
> NULL.
> I mean, all "NA" should be replaced by "NULL" in my database.
> I am trying the command below to pick up the rows and columns with NA
but I
> don't know how to fill the original data :
>
> which(is.na(Alldados),arr.ind=TRUE)
>
> But I don't know how to replace each NA with NULL. I tried using as.null
but
> NA is not replace at all.
Why do you want that? NULL is reserved for objects which emerged from
undefined function results. See its help page.
As such you can not have vector of NULLs.
> rep(NULL, 10)
NULL
> rep(NA, 10)
[1] NA NA NA NA NA NA NA NA NA NA
Maybe you want to replace NA with zero. If yes
Alldados[is.na(Alldados)]<-0
could be what you want.
Regards
Petr
>
> I hope someone could help me.
>
> Best Wishes,
> Nilza Barros
>
>[[alternative HTML version deleted]]
>
> __
> R-help@r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide
http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.
__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Re: [R] Time Series
Although this is not an R question actually, if I get such a question in our consulting centre, my advice is: Present a table of your 4 observations and that's it from a quantitative point of view. There is no sense in modelling or testing with 4 observations. Best, Uwe Ligges On 09.05.2011 16:20, Nicole Gross-Camp wrote: I have what I hope is a simple question - is it possible to do time series analysis on a small data set specifically only four data points? I have collected human threat data (mean number of threats per kilometre walked/ survey) every 3 months in eight different sites (four with an experimental element and four control sites). I am trying to determine the best way to determine if there is a trend in the data though from what I've seen of TSA, our data set is too small. I did a simple paired t-test on the first and average of following three surveys that shows no significant difference but it of course ignores the detail of the latter three surveys. I am not sure how to organize the data for importation into R. I've looked at Crawley and one of Zuur publications but the TS data they work with is much longer term and not over several (independent) sites. Any advice, help, or direction is much appreciated! Best, Nicole Nicole Gross-Camp, PhD Senior Research Associate University of East Anglia Norwich Rwanda: +250 (0)783647398 Skype: nicolegross-camp Based in Rwanda from September 2010 through July 2011: BP 512 Butare Rwanda personal website: http://www.uea.ac.uk/dev/People/Research+Associate/Nicole+Gross-Camp#info project website: www.ReDirectRwanda.com [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] %in% operator - NOT IN
Dan Abner wrote: > I am attempting to use the %in% operator with the ! to produce a NOT IN > type of operation. Just use the ‘%nin‰’ operator in the ‘Hmisc’ package. :-) -- Karl Ove Hufthammer __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] Time Series
I have what I hope is a simple question - is it possible to do time series analysis on a small data set specifically only four data points? I have collected human threat data (mean number of threats per kilometre walked/ survey) every 3 months in eight different sites (four with an experimental element and four control sites). I am trying to determine the best way to determine if there is a trend in the data though from what I've seen of TSA, our data set is too small. I did a simple paired t-test on the first and average of following three surveys that shows no significant difference but it of course ignores the detail of the latter three surveys. I am not sure how to organize the data for importation into R. I've looked at Crawley and one of Zuur publications but the TS data they work with is much longer term and not over several (independent) sites. Any advice, help, or direction is much appreciated! Best, Nicole Nicole Gross-Camp, PhD Senior Research Associate University of East Anglia Norwich Rwanda: +250 (0)783647398 Skype: nicolegross-camp Based in Rwanda from September 2010 through July 2011: BP 512 Butare Rwanda personal website: http://www.uea.ac.uk/dev/People/Research+Associate/Nicole+Gross-Camp#info project website: www.ReDirectRwanda.com [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] How to alter circle size
Thanks for the help! Though, when I do this, I get a message saying "Error
using packet 1 value where TRUE/FALSE." Would that have anything to do with
this set of code?
On Sun, May 8, 2011 at 3:00 PM, Deepayan Sarkar
wrote:
> On Fri, May 6, 2011 at 10:21 PM, Dat Mai wrote:
> > Hello all,
> >
> > I'm trying to create a heatmap using 2 matrices I have: z and v. Both
> > matrices represent different correlations for the same independent
> > variables. The problem I have is that I wish to have the values from
> matrix
> > z to be represented by color intensity while having the values from
> matrix v
> > to be represented by circle size. I currently have the following in front
> of
> > me and an unsure of what to add or change in order to achieve that goal.
> >
> > panel.corrgram.2 =
> > function(x, y, z, subscripts, at = pretty(z), scale = 0.8, ...)
> > {
> > require("grid", quietly = TRUE)
> > x <- as.numeric(x)[subscripts]
> > y <- as.numeric(y)[subscripts]
> > z <- as.numeric(z)[subscripts]
> > zcol <- level.colors(z, at = at, ...)
> > for (i in seq(along = z))
> > {
> >lims <- range(0, z[i])
> >tval <- 2 * base::pi * seq(from = lims[1], to = lims[2], by = 0.01)
> >grid.polygon(x = x[i] + .5 * scale * c(0, sin(tval)),
> > y = y[i] + .5 * scale * c(0, cos(tval)),
> > default.units = "native",
> > gp = gpar(fill = zcol[i]))
> >grid.circle(x = x[i], y = y[i], r = .5 * scale,
> > default.units = "native")
> > }
> > }
>
> Probably this modification
>
> panel.corrgram.2 <-
>function(x, y, z, v, subscripts, at = pretty(v), scale = 0.8, ...)
> {
>require("grid", quietly = TRUE)
>x <- as.numeric(x)[subscripts]
>y <- as.numeric(y)[subscripts]
>z <- as.numeric(z)[subscripts]
> zcol <- level.colors(v, at = at, ...)
>
>
>
>
> followed by
>
> levelplot(signif(z,3), v = v, panel = panel.corrgram.2, ...)
>
> will do it.
>
> -Deepayan
>
>
> >
> > k=levelplot(signif(z,3), scales = list(x = list(rot = 45)),
> > col.regions=col.sch, panel = panel.corrgram.2,
> > label = num.circ, xlab="", ylab="", main=paste(output,"receptor
> response"))
> > print(k)
> >
> > --
> > Best,
> > Dat Mai
> > PhD Rotation Student
> > Albert Einstein College of Medicine
> >
> >[[alternative HTML version deleted]]
> >
> > __
> > R-help@r-project.org mailing list
> > https://stat.ethz.ch/mailman/listinfo/r-help
> > PLEASE do read the posting guide
> http://www.R-project.org/posting-guide.html
> > and provide commented, minimal, self-contained, reproducible code.
> >
>
--
Best,
Dat Mai
PhD Rotation Student
Albert Einstein College of Medicine
[[alternative HTML version deleted]]
__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Re: [R] Summarising by group
Trolling? (but see in line below)
On Mon, May 9, 2011 at 5:12 AM, Martyn Byng wrote:
> I wonder if someone with more experience than me on using R to summarise
> by group wants to post a reply to this
>
> http://www.analyticbridge.com/group/sasandstatisticalprogramming/forum/t
> opics/why-still-use-sas-with-a-lot
>
> To save everyone having to follow the link, the text is copied below
>
> "SAS has some nice features, such as the SQL procedure or simple "group
> by" features. Try to compute correlations "by group" in R: say you have
> 2,000 groups, 2 variables e.g. salary and education level, and 2 million
> observations - you want to compute correlation between salary and
> education within each group.
>
> It is not obvious, your best bet is to use some R package
The wealth of R packages is a core strength of the platform. It is not
a disadvantage to have a wealth of well-developed code for almost any
statistical application.
(see sample
> code on Analyticbridge to do it), and the solution is painful,
Well, the Analyticbridge code is painful, but that example says far
more about the person who wrote it that it does about R. All they
really needed to do was
v <- ddply(xx, .(country), summarize,
COR = cor(income, age),
MEAN_age = mean(age),
MEAN_income = mean(income),
MAX_income = max(income),
STDEV_income = sd(income))
I'm not intested in signing up so I can post a reply to the orignial
post, but feel free to copy my answer there if you want.
Best,
Ista
you can
> not return both correlation and stdev "by group", as the function can
> return only one argument, not a vector. So if you want to return not
> just two, but say 100 metrics, it becomes a nightmare."
Wrong, see example above.
Best,
Ista
>
>
>
>
> The Numerical Algorithms Group Ltd is a company registered in England
> and Wales with company number 1249803. The registered office is:
> Wilkinson House, Jordan Hill Road, Oxford OX2 8DR, United Kingdom.
>
> This e-mail has been scanned for all viruses by Star. Th...{{dropped:4}}
>
> __
> R-help@r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.
>
--
Ista Zahn
Graduate student
University of Rochester
Department of Clinical and Social Psychology
http://yourpsyche.org
__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Re: [R] maximum likelihood convergence reproducing Anderson Blundell 1982 Econometrica R vs Stata
Hmm, I tried replacing the x's in the model with their principal component scores, and suddenly everything converges as a greased lightning: > Z <- princomp(cbind(x1,x2,x3))$scores > Z <- as.data.frame(princomp(cbind(x1,x2,x3))$scores) > names(Z)<- letters[1:3] > optimx(rep(0,8),lnl, hessian=TRUE, y1=y1, y2=y2, + x1=Z$a, x2=Z$b, x3=Z$c, method="BFGS") par 1 0.59107682, 0.01043568, -0.20639153, 0.25902746, 0.24675162, -0.01426477, 0.18045177, -0.23657327 fvalues method fns grs itns conv KKT1 KKT2 xtimes 1 -76.73878 BFGS 157 37 NULL0 TRUE TRUE 0.055 Warning messages: 1: In max(logpar) : no non-missing arguments to max; returning -Inf 2: In min(logpar) : no non-missing arguments to min; returning Inf The likelihood appears to be spot on, but, obviously, the parameter estimates need to be back-transformed to the original x1,x2,x3 system. I'll leave that as the proverbial "exercise for the reader"... However, the whole thing leads me to a suspicion that maybe our numerical gradients are misbehaving in cases with high local collinearity? -pd On May 9, 2011, at 13:40 , Alex Olssen wrote: > Hi Mike, > > Mike said > "is this it, page 1559?" > > That is the front page yes, page 15*6*9 has the table, of which the > model labelled 18s is the one I replicated. > > "did you actually cut/paste code anywhere and is your first > coefficient -.19 or -.019? > Presumably typos would be one possible problem." > > -0.19 is not a typo, it is pi10 in the paper, and a1 in my Stata > estimation - as far as I can tell cutting and pasting is not the > problem. > > "generally it helps if we could at least see the equations to check your > code against typos ( note page number ?) in lnl that may fix part of the > mystery. Is full text available > on author's site, doesn't come up on citeseer AFAICT," > > Unfortunately I do not know of any place to get the full version of > this paper that doesn't require access to a database such as JSTOR. > The fact that this likelihood function reproduces the published > results in Stata makes me confident that it is correct - I also have > read a lot on systems estimation and it is a pretty standard > likelihood function. > > "I guess one question would be " what is beta" in lnl supposed to be - > it isn't used anywhere but I will also mentioned I'm not that familiar > with the R code ( I'm trying to work through this to learn R and the > optimizers). > > maybe some words would help, is sigma supposed to be 2x2 or 8x8 and what are > e1 and e2 supposed to be?" > > The code above is certainly not as elegant as it could be - in this > case the beta is rather superfluous. It is just a vector to hold > parameters - but since I called all the parameters theta anyway there > is no need for it. e1 and e2 are the residuals from the first and > second equations of the system. Sigma is a 2x2 matrix which is the > outer product of the two vectors of residuals. > > Kind regards, > > Alex > > > > On 9 May 2011 23:12, Mike Marchywka wrote: >> >> >> >> >> >> >> >>> Date: Mon, 9 May 2011 22:06:38 +1200 >>> From: alex.ols...@gmail.com >>> To: pda...@gmail.com >>> CC: r-help@r-project.org; da...@otter-rsch.com >>> Subject: Re: [R] maximum likelihood convergence reproducing Anderson >>> Blundell 1982 Econometrica R vs Stata >>> >>> Peter said >>> >>> "Ahem! You might get us interested in your problem, but not to the >>> level that we are going to install Stata and Tsp and actually dig out >>> and study the scientific paper you are talking about. Please cite the >>> results and explain the differences." >>> >>> Apologies Peter, will do, >>> >>> The results which I can emulate in Stata but not (yet) in R are reported >>> below. >> >> did you actually cut/paste code anywhere and is your first coefficient -.19 >> or -.019? >> Presumably typos would be one possible problem. >> >>> They come from Econometrica Vol. 50, No. 6 (Nov., 1982), pp. 1569 >> >> >> is this it, page 1559? >> >> http://www.jstor.org/pss/1913396 >> >> generally it helps if we could at least see the equations to check your >> code against typos ( note page number ?) in lnl that may fix part of the >> mystery. Is full text available >> on author's site, doesn't come up on citeseer AFAICT, >> >> >> http://citeseerx.ist.psu.edu/search?q=blundell+1982&sort=ascdate >> >> I guess one question would be " what is beta" in lnl supposed to be - >> it isn't used anywhere but I will also mentioned I'm not that familiar >> with the R code ( I'm trying to work through this to learn R and the >> optimizers). >> >> maybe some words would help, is sigma supposed to be 2x2 or 8x8 and what are >> e1 and e2 supposed to be? >> >> >> >> >>> >>> TABLE II - model 18s >>> >>> coef std err >>> p10 -0.19 0.078 >>> p11 0.220 0.019 >>> p12 -0.148 0.021 >>> p13 -0.072 >>> p20 0
[R] Using NULL to my data?
Dear R users,
I am reading data from a file where there are some missing that are
represented by -.00.
I am using the command below.
=My original data ===
PARM = TMPC;T12X;T12N;DWPC;PALT;SKNT;DRCT;P24M;CLCL
STNYYMMDD/HHMM TMPC T12X T12N DWPC PALT
SKNT
DRCT P24M CLCL
820420110429/1200 22.50 -.0022.4022.20 -.00
0.00
0.0084.00 4.00
820980110429/1200 26.90 -.0023.4024.10 1010.20
2.91
360.00 2.00 6.00
821130110429/1200 24.30 -.0023.3023.70 -.00
1.94
230.00 3.00 4.00
821410110429/1200 24.40 -.0023.7024.20 1011.80
2.91
===
dados<-read.table("2011042912_teste.dat",sep='',fill=TRUE,na.strings="-.00",skip=4)
head(dados)
V1 V2 V3 V4 V5 V6 V7 V8 group
1 820420 110429/1200 22.5 NA 22.4 22.2 NA 0.00 1
2 0 84.00 4.0 NA NA NA NA NA 1
3 820980 110429/1200 26.9 NA 23.4 24.1 1010.2 2.91 2
43602.00 6.0 NA NA NA NA NA 2
5 821130 110429/1200 24.3 NA 23.3 23.7 NA 1.94 3
62303.00 4.0 NA NA NA NA NA 3
=
After some procedures a have the data as below:
> head(Alldados)
Station_NO date1 T_2M TMAX_2M TMIN_2M TD_2M PS FF_10M DD_10M
1 820420 110429/1200 22.5 NA22.4 22.2 NA 0.00 0
2 820980 110429/1200 26.9 NA23.4 24.1 1010.2 2.91360
3 821130 110429/1200 24.3 NA23.3 23.7 NA 1.94230
4 821410 110429/1200 24.4 NA23.7 24.2 1011.8 2.91270
5 821450 110429/1200 28.2 NA21.1 25.8 1008.8 0.00 0
6 821810 110429/1200 23.3 NA22.8 22.9 1001.6 0.00 0
TOT_PRCP CLCL date2
184.00 NA 2011042912
2 2.00 NA 2011042912
3 3.00 NA 2011042912
412.00 NA 2011042912
5 6.00 NA 2011042912
638.00 NA 2011042912
But I need to feed my database. These missings should be represented by
NULL.
I mean, all "NA" should be replaced by "NULL" in my database.
I am trying the command below to pick up the rows and columns with NA but I
don't know how to fill the original data :
which(is.na(Alldados),arr.ind=TRUE)
But I don't know how to replace each NA with NULL. I tried using as.null but
NA is not replace at all.
I hope someone could help me.
Best Wishes,
Nilza Barros
[[alternative HTML version deleted]]
__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
[R] Round down to earliest hour or half hour
I have times and would like to round down to the earliest 30 minute increment. For instance, a time of 2011-04-28 09:02:00 (the as.numeric value = 1303999320) I would like it to be rounded down to: 2011-04-28 09:00:00 (the as.numeric value = 1303999200) Any ideas of how to do this? - In theory, practice and theory are the same. In practice, they are not - Albert Einstein -- View this message in context: http://r.789695.n4.nabble.com/Round-down-to-earliest-hour-or-half-hour-tp3509374p3509374.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Recursive Indexing Failed
Thank you very much all for your time. For now I am doing this with a simple for loop as some times lapply,sapply makes things more complex (or in other words I am not that experience using it). Best REgards Alex --- On Mon, 5/9/11, Patrick Breheny wrote: > From: Patrick Breheny > Subject: Re: [R] Recursive Indexing Failed > To: "Duncan Murdoch" > Cc: "Alaios" , "R-help@r-project.org" > Date: Monday, May 9, 2011, 2:57 PM > On 05/09/2011 09:52 AM, Duncan > Murdoch wrote: > >> In general, the expression x[[1:2]] is not > meaningful, as the elements > >> of the list may be of different type, with no way > to concatenate them. > > > > That's the wrong explanation: the expression > x[[1:2]] is meaningful, > > but it means the same thing as x[[1]][[2]], not > > c(x[[1]], x[[2]]). > > Thank you for the clarification; I stand corrected. > ___ > Patrick Breheny > Assistant Professor > Department of Biostatistics > Department of Statistics > University of Kentucky > __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Recursive Indexing Failed
On 05/09/2011 09:52 AM, Duncan Murdoch wrote: In general, the expression x[[1:2]] is not meaningful, as the elements of the list may be of different type, with no way to concatenate them. That's the wrong explanation: the expression x[[1:2]] is meaningful, but it means the same thing as x[[1]][[2]], not c(x[[1]], x[[2]]). Thank you for the clarification; I stand corrected. ___ Patrick Breheny Assistant Professor Department of Biostatistics Department of Statistics University of Kentucky __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Recursive Indexing Failed
On 09/05/2011 9:18 AM, Patrick Breheny wrote:
On 05/09/2011 08:58 AM, Alaios wrote:
> Dear all,
> I would like to ask your help concerning an error message I get.
>
> I have the following struct
>
> str(CRagentInTime[[1]])
> List of 2
>$ timelag: int 0
>$ CRagent:List of 50
> ..$ :List of 3
> .. ..$ CRmap: num [1:256, 1:256] NA NA NA NA NA NA NA NA NA NA ...
> .. ..$ xy : num [1:2] 10 177
> .. ..$ sr : num [1:49] -94.9 -92.8 -79.5 -97.6 -78.4 ...
>
> and I wanted to select all the sr fields for every of each one of the 50
CRagent Lists I have.
>
> So I tried something like
>
> str(CRagentInTime[[1]][[2]][[1:10]]$sr) and I get a message that
> Error in CRagentInTime[[1]][[2]][[1:10]] :
> recursive indexing failed at level 3
Selecting multiple elements of a list using an expression like [[1:10]]
does not work. For example:
x<- list("a","b")
x[[1:2]]
produces
Error in x[[1:2]] : subscript out of bounds
In general, the expression x[[1:2]] is not meaningful, as the elements
of the list may be of different type, with no way to concatenate them.
That's the wrong explanation: the expression x[[1:2]] is meaningful,
but it means the same thing as x[[1]][[2]], not
c(x[[1]], x[[2]]).
Duncan Murdoch
>
> strange to me is that this one works
>
> str(CRagentInTime[[1]][[2]][[1]]$sr)
>num [1:49] -106 -92.9 -101.3 -81.9 -96.7 ...
>
>
> I would like to thank you in advance for your help
> Best Regards
> Alex
>
___
Patrick Breheny
Assistant Professor
Department of Biostatistics
Department of Statistics
University of Kentucky
__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Re: [R] Recursive Indexing Failed
On 05/09/2011 09:24 AM, Alaios wrote:
So the only thing that might work is a for..loop to collect all these together?
Best REgards
Alex
You could also use sapply:
x <- list(list(One="a",Two=c("b","c")),list(One="d",Two=c("e","f")))
sapply(x,'[[',"Two")
[,1] [,2]
[1,] "b" "e"
[2,] "c" "f"
In your example, it seems
sapply(CRagentInTime[[1]][[2]],'[[',"sr")
would work, but I am not in a position to replicate your code, as is it
not self-contained.
___
Patrick Breheny
Assistant Professor
Department of Biostatistics
Department of Statistics
University of Kentucky
--- On Mon, 5/9/11, Patrick Breheny wrote:
From: Patrick Breheny
Subject: Re: [R] Recursive Indexing Failed
To: "Alaios"
Cc: "R-help@r-project.org"
Date: Monday, May 9, 2011, 2:18 PM
On 05/09/2011 08:58 AM, Alaios
wrote:
Dear all,
I would like to ask your help concerning an error
message I get.
I have the following struct
str(CRagentInTime[[1]])
List of 2
$ timelag: int 0
$ CRagent:List of 50
..$ :List of 3
.. ..$ CRmap: num [1:256, 1:256] NA NA NA
NA NA NA NA NA NA NA ...
.. ..$ xy : num [1:2] 10
177
.. ..$ sr : num [1:49]
-94.9 -92.8 -79.5 -97.6 -78.4 ...
and I wanted to select all the sr fields for every of
each one of the 50 CRagent Lists I have.
So I tried something like
str(CRagentInTime[[1]][[2]][[1:10]]$sr) and I get a
message that
Error in CRagentInTime[[1]][[2]][[1:10]] :
recursive indexing failed at level 3
Selecting multiple elements of a list using an expression
like [[1:10]]
does not work. For example:
x<- list("a","b")
x[[1:2]]
produces
Error in x[[1:2]] : subscript out of bounds
In general, the expression x[[1:2]] is not meaningful, as
the elements
of the list may be of different type, with no way to
concatenate them.
strange to me is that this one works
str(CRagentInTime[[1]][[2]][[1]]$sr)
num [1:49] -106 -92.9 -101.3 -81.9
-96.7 ...
I would like to thank you in advance for your help
Best Regards
Alex
___
Patrick Breheny
Assistant Professor
Department of Biostatistics
Department of Statistics
University of Kentucky
__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
[R] Create subsets of data
Hello All, Let's say I have points on a x-y plane. x ranges from 0-2 and y from 0-2. There are points in quadrants x[0:1]---y[0:1] and in x[1:2]y[1:2]. I would like to get the mean and std of the points in the x[0:1]y[0:1] quadrant alone. Is there a straight forward way to do it? I asked a similar question a few days ago regarding plotting a subset of data using conditions. The solution was: http://r.789695.n4.nabble.com/Conditional-plot-length-in-R-td3503855.html Thank you, Why-so-serious. [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Recursive Indexing Failed
On May 9, 2011, at 15:24 , Alaios wrote:
> So the only thing that might work is a for..loop to collect all these
> together?
An implicit loop using lapply/sapply might be more like it:
lapply(CRagentInTime[[1]]$CRagent[1:10], "[[", "sr")
Notice that fancy indexing usually requires "[", not "[[".
>
> Best REgards
> Alex
>
> --- On Mon, 5/9/11, Patrick Breheny wrote:
>
>> From: Patrick Breheny
>> Subject: Re: [R] Recursive Indexing Failed
>> To: "Alaios"
>> Cc: "R-help@r-project.org"
>> Date: Monday, May 9, 2011, 2:18 PM
>> On 05/09/2011 08:58 AM, Alaios
>> wrote:
>>> Dear all,
>>> I would like to ask your help concerning an error
>> message I get.
>>>
>>> I have the following struct
>>>
>>> str(CRagentInTime[[1]])
>>> List of 2
>>>$ timelag: int 0
>>>$ CRagent:List of 50
>>> ..$ :List of 3
>>> .. ..$ CRmap: num [1:256, 1:256] NA NA NA
>> NA NA NA NA NA NA NA ...
>>> .. ..$ xy : num [1:2] 10
>> 177
>>> .. ..$ sr : num [1:49]
>> -94.9 -92.8 -79.5 -97.6 -78.4 ...
>>>
>>> and I wanted to select all the sr fields for every of
>> each one of the 50 CRagent Lists I have.
>>>
>>> So I tried something like
>>>
>>> str(CRagentInTime[[1]][[2]][[1:10]]$sr) and I get a
>> message that
>>> Error in CRagentInTime[[1]][[2]][[1:10]] :
>>> recursive indexing failed at level 3
>>
>> Selecting multiple elements of a list using an expression
>> like [[1:10]]
>> does not work. For example:
>>
>> x <- list("a","b")
>> x[[1:2]]
>>
>> produces
>>
>> Error in x[[1:2]] : subscript out of bounds
>>
>> In general, the expression x[[1:2]] is not meaningful, as
>> the elements
>> of the list may be of different type, with no way to
>> concatenate them.
>>
>>>
>>> strange to me is that this one works
>>>
>>> str(CRagentInTime[[1]][[2]][[1]]$sr)
>>>num [1:49] -106 -92.9 -101.3 -81.9
>> -96.7 ...
>>>
>>>
>>> I would like to thank you in advance for your help
>>> Best Regards
>>> Alex
>>>
>> ___
>> Patrick Breheny
>> Assistant Professor
>> Department of Biostatistics
>> Department of Statistics
>> University of Kentucky
>>
>
> __
> R-help@r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.
--
Peter Dalgaard
Center for Statistics, Copenhagen Business School
Solbjerg Plads 3, 2000 Frederiksberg, Denmark
Phone: (+45)38153501
Email: pd@cbs.dk Priv: pda...@gmail.com
__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Re: [R] Recursive Indexing Failed
So the only thing that might work is a for..loop to collect all these together?
Best REgards
Alex
--- On Mon, 5/9/11, Patrick Breheny wrote:
> From: Patrick Breheny
> Subject: Re: [R] Recursive Indexing Failed
> To: "Alaios"
> Cc: "R-help@r-project.org"
> Date: Monday, May 9, 2011, 2:18 PM
> On 05/09/2011 08:58 AM, Alaios
> wrote:
> > Dear all,
> > I would like to ask your help concerning an error
> message I get.
> >
> > I have the following struct
> >
> > str(CRagentInTime[[1]])
> > List of 2
> > $ timelag: int 0
> > $ CRagent:List of 50
> > ..$ :List of 3
> > .. ..$ CRmap: num [1:256, 1:256] NA NA NA
> NA NA NA NA NA NA NA ...
> > .. ..$ xy : num [1:2] 10
> 177
> > .. ..$ sr : num [1:49]
> -94.9 -92.8 -79.5 -97.6 -78.4 ...
> >
> > and I wanted to select all the sr fields for every of
> each one of the 50 CRagent Lists I have.
> >
> > So I tried something like
> >
> > str(CRagentInTime[[1]][[2]][[1:10]]$sr) and I get a
> message that
> > Error in CRagentInTime[[1]][[2]][[1:10]] :
> > recursive indexing failed at level 3
>
> Selecting multiple elements of a list using an expression
> like [[1:10]]
> does not work. For example:
>
> x <- list("a","b")
> x[[1:2]]
>
> produces
>
> Error in x[[1:2]] : subscript out of bounds
>
> In general, the expression x[[1:2]] is not meaningful, as
> the elements
> of the list may be of different type, with no way to
> concatenate them.
>
> >
> > strange to me is that this one works
> >
> > str(CRagentInTime[[1]][[2]][[1]]$sr)
> > num [1:49] -106 -92.9 -101.3 -81.9
> -96.7 ...
> >
> >
> > I would like to thank you in advance for your help
> > Best Regards
> > Alex
> >
> ___
> Patrick Breheny
> Assistant Professor
> Department of Biostatistics
> Department of Statistics
> University of Kentucky
>
__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Re: [R] Recursive Indexing Failed
On 05/09/2011 08:58 AM, Alaios wrote:
Dear all,
I would like to ask your help concerning an error message I get.
I have the following struct
str(CRagentInTime[[1]])
List of 2
$ timelag: int 0
$ CRagent:List of 50
..$ :List of 3
.. ..$ CRmap: num [1:256, 1:256] NA NA NA NA NA NA NA NA NA NA ...
.. ..$ xy : num [1:2] 10 177
.. ..$ sr : num [1:49] -94.9 -92.8 -79.5 -97.6 -78.4 ...
and I wanted to select all the sr fields for every of each one of the 50
CRagent Lists I have.
So I tried something like
str(CRagentInTime[[1]][[2]][[1:10]]$sr) and I get a message that
Error in CRagentInTime[[1]][[2]][[1:10]] :
recursive indexing failed at level 3
Selecting multiple elements of a list using an expression like [[1:10]]
does not work. For example:
x <- list("a","b")
x[[1:2]]
produces
Error in x[[1:2]] : subscript out of bounds
In general, the expression x[[1:2]] is not meaningful, as the elements
of the list may be of different type, with no way to concatenate them.
strange to me is that this one works
str(CRagentInTime[[1]][[2]][[1]]$sr)
num [1:49] -106 -92.9 -101.3 -81.9 -96.7 ...
I would like to thank you in advance for your help
Best Regards
Alex
___
Patrick Breheny
Assistant Professor
Department of Biostatistics
Department of Statistics
University of Kentucky
__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Re: [R] Weighted box or violin plots in Lattice?
On Mon, May 9, 2011 at 5:42 PM, David Winsemius wrote: > > On May 9, 2011, at 12:35 AM, Deepayan Sarkar wrote: > >> On Mon, May 9, 2011 at 2:20 AM, Thomas Lumley wrote: >>> >>> On Mon, May 9, 2011 at 6:35 AM, Deepayan Sarkar >>> wrote: On Sat, May 7, 2011 at 1:55 AM, Raphael Mazor wrote: > > Is it possible to create weighted boxplots or violin plots in lattice? > > It seems that you can specify weights for panel.histogram() and > panel.densityplot(), but not for panel.bwplot or panel.violin(). Not for panel.histogram() either. It's not immediately obvious how you would get weighted boxplots. >>> >>> The way the survey world does it is to get weighted quantiles and work >>> from them, as in survey:::svyboxplot(). The only tricky decision is >>> what to do with outliers, since I haven't been able to think of any >>> good way of indicating weights on them. >> >> So I guess with bwplot() one would have to write a version of >> boxplot.stats() that uses weighted quantiles, and then write a >> modified panel function. >> >> A crude approximation (if the weights don't vary too much) may be to >> scale and round the weights to integers, and then repeat each data >> point; e.g., newx <- rep(x, w), etc. > > You could do a bit better if you just substituted wtd.quantile from Hmisc > with an x and weights argument for the fivenum call in boxplot.stats. Thanks for that pointer. Incorporating weights into panel.bwplot() would still be a bit painful though (more so than panel.violin). -Deepayan > > require(Hmisc) >> ?wtd.quantile >> fivenum(x=1:10) > [1] 1.0 3.0 5.5 8.0 10.0 >> wtd.quantile(x=1:10) > 0% 25% 50% 75% 100% > 1.00 3.25 5.50 7.75 10.00 >> wtd.quantile( x = 1:10, weights = 1:10) > 0% 25% 50% 75% 100% > 1 5 7 9 10 > > (Most people think the hinges are at the 25th and 75th percentiles anyway.) > > >> >> -Deepayan >> >> __ >> R-help@r-project.org mailing list >> https://stat.ethz.ch/mailman/listinfo/r-help >> PLEASE do read the posting guide >> http://www.R-project.org/posting-guide.html >> and provide commented, minimal, self-contained, reproducible code. > > David Winsemius, MD > West Hartford, CT > > __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] Recursive Indexing Failed
Dear all, I would like to ask your help concerning an error message I get. I have the following struct str(CRagentInTime[[1]]) List of 2 $ timelag: int 0 $ CRagent:List of 50 ..$ :List of 3 .. ..$ CRmap: num [1:256, 1:256] NA NA NA NA NA NA NA NA NA NA ... .. ..$ xy : num [1:2] 10 177 .. ..$ sr : num [1:49] -94.9 -92.8 -79.5 -97.6 -78.4 ... and I wanted to select all the sr fields for every of each one of the 50 CRagent Lists I have. So I tried something like str(CRagentInTime[[1]][[2]][[1:10]]$sr) and I get a message that Error in CRagentInTime[[1]][[2]][[1:10]] : recursive indexing failed at level 3 strange to me is that this one works str(CRagentInTime[[1]][[2]][[1]]$sr) num [1:49] -106 -92.9 -101.3 -81.9 -96.7 ... I would like to thank you in advance for your help Best Regards Alex __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] maximum likelihood convergence reproducing Anderson Blundell 1982 Econometrica R vs Stata
On May 9, 2011, at 13:40 , Alex Olssen wrote: > Hi Mike, > > Mike said > "is this it, page 1559?" > > That is the front page yes, page 15*6*9 has the table, of which the > model labelled 18s is the one I replicated. > However, the R code you posted will at best replicate model 18. For 18s, you need to impose symmetry conditions. The fit of model 18 does seem to give similar results to those in Table II, but not exactly. Even more puzzling, if you start from the published coefficients, nlm seems to be getting stuck at a non-concave point of the negative likelihood. > nlm(p=ab, f=lnl, hessian=TRUE, y1=y1, y2=y2, + x1=x1, x2=x2, x3=x3, gradtol=1e-15) $minimum [1] -76.60681 $estimate [1] -0.64701504 0.27284992 -0.13713084 -0.07205753 1.28200342 -0.24596766 0.13502787 0.06001181 $gradient [1] 2.782425 12.648629 -1.830244 -29.296795 -2.577734 -4.954042 1.495517 11.016190 $hessian [,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8] [1,] 197435.9 1977197 1741724 805132.7 135821.9 1358013 1196714 553746 [2,] 1977197.4 19712076 17383474 8064540.2 1359856.0 13527720 11935305 5544903 [3,] 1741724.0 17383474 15336008 7121047.7 1197868.5 11929667 10529439 4896008 [4,] 805132.7 8064540 7121048 3315377.8 553733.1 5534923 4889523 2279404 [5,] 135821.9 1359856 1197868 553733.1 271511.7 2713733 2391332 1106572 [6,] 1358012.7 13527720 11929667 5534923.0 2713732.9 26955636 23784039 11054174 [7,] 1196714.3 11935305 10529439 4889522.6 2391331.9 23784039 20993413 9765022 [8,] 553746.0 5544903 4896008 2279404.1 1106571.9 11054174 9765022 4552693 $code [1] 2 $iterations [1] 4 -- Peter Dalgaard Center for Statistics, Copenhagen Business School Solbjerg Plads 3, 2000 Frederiksberg, Denmark Phone: (+45)38153501 Email: pd@cbs.dk Priv: pda...@gmail.com __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] rquest for help
On 05/09/2011 01:19 AM, Pawan Kakchingtabam wrote: Sir, Kindlly Guide me how to get the R CELFILES. I have install R but I cannat asses the command: Data<- ReadAffy() and I got the error: Error in AllButCelsForReadAffy(..., filenames = filenames, widget = widget, : No cel filennames specified and no cel files in specified directory:C:/Documents and Settings/pawan.k/Desktop. Pawan -- please ask questions about Bioconductor packages on the Bioconductor mailing list. http://bioconductor.org/help/mailing-list/ Consult the help page for ReadAffy, ?ReadAffy, and setwd() to the directory containing the CEL files. Martin Wit regds, Pawan This e-mail contains PRIVILEGED AND CONFIDENTIAL INFORMATION intended solely for the use of the addressee(s). If you are not the intended recipient, please notify the sender by e-mail and delete the original message. Further, you are not to copy, disclose, or distribute this e-mail or its contents to any other person and any such actions that are unlawful. This e-mail may contain viruses. Ocimum Biosolutions has taken every reasonable precaution to minimize this risk, but is not liable for any damage you may sustain as a result of any virus in this e-mail. You should carry out your own virus checks before opening the e-mail or attachment. The information contained in this email and any attachments is confidential and may be subject to copyright or other intellectual property protection. If you are not the intended recipient, you are not authorized to use or disclose this information, and we request that you notify us by reply mail or telephone and delete the original message from your mail system. OCIMUMBIO SOLUTIONS (P) LTD [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. -- Computational Biology Fred Hutchinson Cancer Research Center 1100 Fairview Ave. N. PO Box 19024 Seattle, WA 98109 Location: M1-B861 Telephone: 206 667-2793 __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] coxph and survfit issue - strata
> Dear users, > > In a study with recurrent events: > My objective is to get estimates of survival (obtained through a Cox > model) by rank of recurrence and by treatment group. > With the following code (corresponding to a model with a global > effect of the treatment=rx), I get no error and manage to obtain > what I want : > data<-(bladder) > model1<-coxph(Surv(stop,event)~rx+strata(enum) > +cluster(id),data=bladder) > data1<-data.frame(rx=1) > survfit(model1,newdata=data1) > > But with the model with strata by treatment interaction > (corresponding to a model with an effect of the treatment by rank), > I get the following error: > model2<-coxph(Surv(stop,event)~rx*strata(enum) > +cluster(id),data=bladder) > > data1<-data.frame(rx=1) > > survfit(model2,newdata=data1) > Erreur dans strata(enum) : objet "enum" non trouv? =>error in > strata(enum) : object "enum" not found You have neglected to tell us what version of R and of the survival library you are using. (As the author, I always have the newest version of course.) The example you gave works if there is no "cluster" statement. Your error is a surprise to me and I will look into it. Terry Therneau __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] Mixed-design ANOVA: 2 between-subject factors and 1 within-subject factor
Dear all,
I am trying to using a mixed-design ANOVA to analyze my data. I have two
between subject variables: location (2 different locations) and age group
(young and old), and one within-subject variable: valence (positive,
neutral, negative).
I am looking at an Stevens(one between, two within) in Notes on the use of R
for psychology experiments and questionnaires (P34 in this article).
In Stevens' example, he first create a matrix and put the data in a
multivariate format using cbind.data.frame() function.
Ela.mat <- matrix (c(19,.28), nrow=16, byrow=T)
Ela.mul <- cbind.data.frame(subj=1:16, gp=factor(rep(1:2,rep(8,2))),
Ela.mat)
dimnames(Ela.mul)[[2]] <-
c("subj","gp","d11","d12","d13","d21","d22","d23")
My data includes 447 data points:
5,4,5,
2,1,4,
4,7,8,
0,4,5,
3,1,7,
1,4,2,
3,2,5,
2,5,6,
4,2,6,
..
The three columns are positive, neutral and negative. First 31 rows are
Young* location 1, next 39 Old* location1, next 43 Young* location2, and
the final 36 Old *location2.
I have 2 grouping variables and thus 4 uneven groups. Any suggestion for how
I can group them in cbind.data.frame()?
Or is there any suggestion for how to analyze in this 3 (valence: positive,
negative, neutral) X 2 (age: young vs. old) X 2 (location: a vs. b) mixed
Analysis of Variance (ANOVA)?
Thank you very much. Any and all help will be immensely appreciated.
--
View this message in context:
http://r.789695.n4.nabble.com/Mixed-design-ANOVA-2-between-subject-factors-and-1-within-subject-factor-tp3508819p3508819.html
Sent from the R help mailing list archive at Nabble.com.
__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
[R] rquest for help
Sir, Kindlly Guide me how to get the R CELFILES. I have install R but I cannat asses the command: Data <- ReadAffy() and I got the error: Error in AllButCelsForReadAffy(..., filenames = filenames, widget = widget, : No cel filennames specified and no cel files in specified directory:C:/Documents and Settings/pawan.k/Desktop. Wit regds, Pawan This e-mail contains PRIVILEGED AND CONFIDENTIAL INFORMATION intended solely for the use of the addressee(s). If you are not the intended recipient, please notify the sender by e-mail and delete the original message. Further, you are not to copy, disclose, or distribute this e-mail or its contents to any other person and any such actions that are unlawful. This e-mail may contain viruses. Ocimum Biosolutions has taken every reasonable precaution to minimize this risk, but is not liable for any damage you may sustain as a result of any virus in this e-mail. You should carry out your own virus checks before opening the e-mail or attachment. The information contained in this email and any attachments is confidential and may be subject to copyright or other intellectual property protection. If you are not the intended recipient, you are not authorized to use or disclose this information, and we request that you notify us by reply mail or telephone and delete the original message from your mail system. OCIMUMBIO SOLUTIONS (P) LTD [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] maximum likelihood convergence reproducing Anderson Blundell 1982 Econometrica R vs Stata
> Date: Mon, 9 May 2011 22:06:38 +1200 > From: alex.ols...@gmail.com > To: pda...@gmail.com > CC: r-help@r-project.org; da...@otter-rsch.com > Subject: Re: [R] maximum likelihood convergence reproducing Anderson Blundell > 1982 Econometrica R vs Stata > > Peter said > > "Ahem! You might get us interested in your problem, but not to the > level that we are going to install Stata and Tsp and actually dig out > and study the scientific paper you are talking about. Please cite the > results and explain the differences." > > Apologies Peter, will do, > > The results which I can emulate in Stata but not (yet) in R are reported > below. did you actually cut/paste code anywhere and is your first coefficient -.19 or -.019? Presumably typos would be one possible problem. > They come from Econometrica Vol. 50, No. 6 (Nov., 1982), pp. 1569 is this it, page 1559? http://www.jstor.org/pss/1913396 generally it helps if we could at least see the equations to check your code against typos ( note page number ?) in lnl that may fix part of the mystery. Is full text available on author's site, doesn't come up on citeseer AFAICT, http://citeseerx.ist.psu.edu/search?q=blundell+1982&sort=ascdate I guess one question would be " what is beta" in lnl supposed to be - it isn't used anywhere but I will also mentioned I'm not that familiar with the R code ( I'm trying to work through this to learn R and the optimizers). maybe some words would help, is sigma supposed to be 2x2 or 8x8 and what are e1 and e2 supposed to be? > > TABLE II - model 18s > > coef std err > p10 -0.19 0.078 > p11 0.220 0.019 > p12 -0.148 0.021 > p13 -0.072 > p20 0.893 0.072 > p21 -0.148 > p22 0.050 0.035 > p23 0.098 > > The results which I produced in Stata are reported below. > I spent the last hour rewriting the code to reproduce this - since I > am now at home and not at work :( > My results are "identical" to those published. The estimates are for > a 3 equation symmetrical singular system. > I have not bothered to report symmetrical results and have backed out > an extra estimate using adding up constraints. > I have also backed out all standard errors using the delta method. > > . ereturn display > -- > | Coef. Std. Err. z P>|z| [95% Conf. Interval] > -+ > a | > a1 | -.0188115 .0767759 -0.25 0.806 -.1692895 .1316664 > a2 | .8926598 .0704068 12.68 0.000 .7546651 1.030655 > a3 | .1261517 .0590193 2.14 0.033 .010476 .2418275 > -+ > g | > g11 | .2199442 .0184075 11.95 0.000 .183866 .2560223 > g12 | -.1476856 .0211982 -6.97 0.000 -.1892334 -.1061378 > g13 | -.0722586 .0145154 -4.98 0.000 -.1007082 -.0438089 > g22 | .0496865 .0348052 1.43 0.153 -.0185305 .1179034 > g23 | .0979991 .0174397 5.62 0.000 .0638179 .1321803 > g33 | -.0257405 .0113869 -2.26 0.024 -.0480584 -.0034226 > -- > > In R I cannot get results like this - I think it is probably to do > with my inability at using the optimisers well. > Any pointers would be appreciated. > > Peter said "Are we maximizing over the same parameter space? You say > that the estimates from the paper gives a log-likelihood of 54.04, but > the exact solution clocked in at 76.74, which in my book is rather > larger." > > I meant +54.04 > -76.74. It is quite common to get positive > log-likelihoods in these system estimation. > > Kind regards, > > Alex > > On 9 May 2011 19:04, peter dalgaard wrote: > > > > On May 9, 2011, at 06:07 , Alex Olssen wrote: > > > >> Thank you all for your input. > >> > >> Unfortunately my problem is not yet resolved. Before I respond to > >> individual comments I make a clarification: > >> > >> In Stata, using the same likelihood function as above, I can reproduce > >> EXACTLY (to 3 decimal places or more, which is exactly considering I > >> am using different software) the results from model 8 of the paper. > >> > >> I take this as an indication that I am using the same likelihood > >> function as the authors, and that it does indeed work. > >> The reason I am trying to estimate the model in R is because while > >> Stata reproduces model 8 perfectly it has convergence > >> difficulties for some of the other models. > >> > >> Peter Dalgaard, > >> > >> "Better starting values would help. In this case, almost too good > >> values are available: > >> > >> start <- c(coef(lm(y1~x1+x2+x3)), coef(lm(y2~x1+x2+x3))) > >> > >> which appears to be the _exact_ solution." > >> > >> Thanks for the suggestion. Using these starting values produces the > >> exact estimate that Dave Fournier emailed me. > >> If these are the exact solution then why did the author publish > >> different answers which are completely reproducible in > >> Stata and
Re: [R] Hosmer-Lemeshow 'goodness of fit'
The test in the rms package's residuals.lrm function is the le Cessie - van Houwelingen - Copas - Hosmer unweighted sum of squares test for global goodness of fit. Like all statistical tests, a large P-value has no information other than there was not sufficient evidence to reject the null hypothesis. Here the null hypothesis is that the true probabilities are those specified by the model. Such an omnibus test, though having good general power (better than Hosmer-Lemeshow) lacks power to detect specific alternatives. That's why I spend more time allowing for nonlinearity of predictors. Frank viostorm wrote: > > Again, thanks so much for your help. > > Is there a "for dummies" version for interpreting the le Cessie and > Houwelingen test. I read the 1991 biometrics paper but honestly got lost > in the math. > > Is it interpreted the same way the Hosmer-Lemeshow test is? ie, a > non-significant result means model fits well. > > I guess what does, what would my p-value of p=0.284362 tell you about my > model? > > I would like to describe the goodness of fit of my model in a paper but > I'm worried the average medical reader would not know how to interpret the > result of this test whereas there are lots of references on interpreting > Hosmer-Lemeshow. > > (my cross validated c-statistic was 0.69 and r^2 was 0.15) > > Thanks again for your all help! (also with my k-fold crossvalidation > question!) > > -Rob > > > Robert Schutt, MD, MCS > Resident - Department of Internal Medicine > University of Virginia, Charlottesville, Virginia > - Frank Harrell Department of Biostatistics, Vanderbilt University -- View this message in context: http://r.789695.n4.nabble.com/Hosmer-Lemeshow-goodness-of-fit-tp3508127p3509102.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Weighted box or violin plots in Lattice?
On May 9, 2011, at 12:35 AM, Deepayan Sarkar wrote: On Mon, May 9, 2011 at 2:20 AM, Thomas Lumley wrote: On Mon, May 9, 2011 at 6:35 AM, Deepayan Sarkar wrote: On Sat, May 7, 2011 at 1:55 AM, Raphael Mazor wrote: Is it possible to create weighted boxplots or violin plots in lattice? It seems that you can specify weights for panel.histogram() and panel.densityplot(), but not for panel.bwplot or panel.violin(). Not for panel.histogram() either. It's not immediately obvious how you would get weighted boxplots. The way the survey world does it is to get weighted quantiles and work from them, as in survey:::svyboxplot(). The only tricky decision is what to do with outliers, since I haven't been able to think of any good way of indicating weights on them. So I guess with bwplot() one would have to write a version of boxplot.stats() that uses weighted quantiles, and then write a modified panel function. A crude approximation (if the weights don't vary too much) may be to scale and round the weights to integers, and then repeat each data point; e.g., newx <- rep(x, w), etc. You could do a bit better if you just substituted wtd.quantile from Hmisc with an x and weights argument for the fivenum call in boxplot.stats. require(Hmisc) > ?wtd.quantile > fivenum(x=1:10) [1] 1.0 3.0 5.5 8.0 10.0 > wtd.quantile(x=1:10) 0% 25% 50% 75% 100% 1.00 3.25 5.50 7.75 10.00 > wtd.quantile( x = 1:10, weights = 1:10) 0% 25% 50% 75% 100% 1579 10 (Most people think the hinges are at the 25th and 75th percentiles anyway.) -Deepayan __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. David Winsemius, MD West Hartford, CT __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Suppressing iterations in DEoptim
On 09.05.2011 14:03, arnab.ma...@dc.ibm.com wrote: Dear Uwe, I already have gone through that document. But I could not find the solution. I tiold you that help page points us to the help page for ?DEoptim.control and that one has an argument "trace". Please read both, my original message as well as the help pages. Uwe Ligges Thanks& Regards Arnab Kumar Maity || IBM Global Process Services || || 2nd Floor, VBC Solitaire || || 47& 49, Bazullah Road || T Nagar || || Chennai - 600017 || India || || Email: arnab.ma...@dc.ibm.com || || Ph: +91 8939390048 || Uwe Ligges To arnab.ma...@dc.ibm.com 05/09/2011 05:29 cc PMr-help@r-project.org Subject Re: [R] Suppressing iterations in DEoptim On 09.05.2011 13:47, arnab.ma...@dc.ibm.com wrote: Dear Uwe, Which help file you are talking about? The one you get when typing ?DEoptim which one do you think is more appropriate for getting help on DEoptim ? Uwe Thanks& Regards Arnab Kumar Maity || IBM Global Process Services || || 2nd Floor, VBC Solitaire || || 47& 49, Bazullah Road || T Nagar || || Chennai - 600017 || India || || Email: arnab.ma...@dc.ibm.com || || Ph: +91 8939390048 || Uwe Ligges To arnab.ma...@dc.ibm.com 05/09/2011 04:24 cc PMr-help@r-project.org Subject Re: [R] Suppressing iterations in DEoptim On 09.05.2011 11:06, arnab.ma...@dc.ibm.com wrote: Dear R users, During the the running of DEoptim function which belongs to "DEoptim" package it automatically gives the output like the following: Iteration: 1 bestvalit: 181.379847 bestmemit:0.2264991.395852 Iteration: 2 bestvalit: 14.062649 bestmemit:2.2903575.597838 Iteration: 3 bestvalit: 14.062649 bestmemit:2.2903575.597838 Iteration: 4 bestvalit: 14.062649 bestmemit:2.2903575.597838 Iteration: 5 bestvalit: 14.062649 bestmemit:2.2903575.597838 Iteration: 6 bestvalit: 14.062649 bestmemit:2.2903575.597838 Iteration: 7 bestvalit: 14.062649 bestmemit:2.2903575.597838 Iteration: 8 bestvalit: 12.952513 bestmemit:2.7157097.691444 Iteration: 9 bestvalit: 3.254643 bestmemit:2.3901515.597838 Iteration: 10 bestvalit: 3.254643 bestmemit:2.3901515.597838 Iteration: 11 bestvalit: 1.820207 bestmemit:2.1707184.779070 Iteration: 12 bestvalit: 1.205168 bestmemit:1.8016293.320871 Iteration: 13 bestvalit: 1.101356 bestmemit:1.5871302.605967 Is their any procedure to suppress this i.e not to print this information? Yes, the procedure is to read the help file, as you have been asked by the posting guide before posting. ?DEoptim points you to the help for ?DEoptim.control which has a trace argument that seems to be useful ... Uwe Ligges Thank you for your kind reply. Thanks&Regards Arnab Kumar Maity || IBM Global Process Services || || 2nd Floor, VBC Solitaire || || 47&49, Bazullah Road || T Nagar || || Chennai - 600017 || India || || Email: arnab.ma...@dc.ibm.com || || Ph: +91 8939390048 || __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Suppressing iterations in DEoptim
Dear Uwe, I already have gone through that document. But I could not find the solution. Thanks & Regards Arnab Kumar Maity || IBM Global Process Services || || 2nd Floor, VBC Solitaire || || 47 & 49, Bazullah Road || T Nagar || || Chennai - 600017 || India || || Email: arnab.ma...@dc.ibm.com || || Ph: +91 8939390048 || Uwe Ligges To arnab.ma...@dc.ibm.com 05/09/2011 05:29 cc PMr-help@r-project.org Subject Re: [R] Suppressing iterations in DEoptim On 09.05.2011 13:47, arnab.ma...@dc.ibm.com wrote: > Dear Uwe, > > Which help file you are talking about? The one you get when typing ?DEoptim which one do you think is more appropriate for getting help on DEoptim ? Uwe > > Thanks& Regards > > Arnab Kumar Maity > > || IBM Global Process Services || > || 2nd Floor, VBC Solitaire || > || 47& 49, Bazullah Road || T Nagar || > || Chennai - 600017 || India || > || Email: arnab.ma...@dc.ibm.com || > || Ph: +91 8939390048 || > > > > Uwe Ligges > .tu-dortmund.de> To > arnab.ma...@dc.ibm.com > 05/09/2011 04:24 cc > PMr-help@r-project.org > Subject > Re: [R] Suppressing iterations in > DEoptim > > > > > > > > > > > > > On 09.05.2011 11:06, arnab.ma...@dc.ibm.com wrote: >> >> Dear R users, >> >> During the the running of DEoptim function which belongs to "DEoptim" >> package it automatically gives the output like the following: >> >> Iteration: 1 bestvalit: 181.379847 bestmemit:0.2264991.395852 >> Iteration: 2 bestvalit: 14.062649 bestmemit:2.2903575.597838 >> Iteration: 3 bestvalit: 14.062649 bestmemit:2.2903575.597838 >> Iteration: 4 bestvalit: 14.062649 bestmemit:2.2903575.597838 >> Iteration: 5 bestvalit: 14.062649 bestmemit:2.2903575.597838 >> Iteration: 6 bestvalit: 14.062649 bestmemit:2.2903575.597838 >> Iteration: 7 bestvalit: 14.062649 bestmemit:2.2903575.597838 >> Iteration: 8 bestvalit: 12.952513 bestmemit:2.7157097.691444 >> Iteration: 9 bestvalit: 3.254643 bestmemit:2.3901515.597838 >> Iteration: 10 bestvalit: 3.254643 bestmemit:2.3901515.597838 >> Iteration: 11 bestvalit: 1.820207 bestmemit:2.1707184.779070 >> Iteration: 12 bestvalit: 1.205168 bestmemit:1.8016293.320871 >> Iteration: 13 bestvalit: 1.101356 bestmemit:1.5871302.605967 >> >> Is their any procedure to suppress this i.e not to print this > information? > > Yes, the procedure is to read the help file, as you have been asked by > the posting guide before posting. > > ?DEoptim points you to the help for ?DEoptim.control which has a trace > argument that seems to be useful ... > > Uwe Ligges > > > >> Thank you for your kind reply. >> >> >> >> Thanks& Regards >> >> Arnab Kumar Maity >> >> || IBM Global Process Services || >> || 2nd Floor, VBC Solitaire || >> || 47& 49, Bazullah Road || T Nagar || >> || Chennai - 600017 || India || >> || Email: arnab.ma...@dc.ibm.com || >> || Ph: +91 8939390048 || >> >> __ >> R-help@r-project.org mailing list >> https://stat.ethz.ch/mailman/listinfo/r-help >> PLEASE do read the posting guide > http://www.R-project.org/posting-guide.html >> and provide commented, minimal, self-contained, reproducible code. > > __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Suppressing iterations in DEoptim
On 09.05.2011 13:47, arnab.ma...@dc.ibm.com wrote: Dear Uwe, Which help file you are talking about? The one you get when typing ?DEoptim which one do you think is more appropriate for getting help on DEoptim ? Uwe Thanks& Regards Arnab Kumar Maity || IBM Global Process Services || || 2nd Floor, VBC Solitaire || || 47& 49, Bazullah Road || T Nagar || || Chennai - 600017 || India || || Email: arnab.ma...@dc.ibm.com || || Ph: +91 8939390048 || Uwe Ligges To arnab.ma...@dc.ibm.com 05/09/2011 04:24 cc PMr-help@r-project.org Subject Re: [R] Suppressing iterations in DEoptim On 09.05.2011 11:06, arnab.ma...@dc.ibm.com wrote: Dear R users, During the the running of DEoptim function which belongs to "DEoptim" package it automatically gives the output like the following: Iteration: 1 bestvalit: 181.379847 bestmemit:0.2264991.395852 Iteration: 2 bestvalit: 14.062649 bestmemit:2.2903575.597838 Iteration: 3 bestvalit: 14.062649 bestmemit:2.2903575.597838 Iteration: 4 bestvalit: 14.062649 bestmemit:2.2903575.597838 Iteration: 5 bestvalit: 14.062649 bestmemit:2.2903575.597838 Iteration: 6 bestvalit: 14.062649 bestmemit:2.2903575.597838 Iteration: 7 bestvalit: 14.062649 bestmemit:2.2903575.597838 Iteration: 8 bestvalit: 12.952513 bestmemit:2.7157097.691444 Iteration: 9 bestvalit: 3.254643 bestmemit:2.3901515.597838 Iteration: 10 bestvalit: 3.254643 bestmemit:2.3901515.597838 Iteration: 11 bestvalit: 1.820207 bestmemit:2.1707184.779070 Iteration: 12 bestvalit: 1.205168 bestmemit:1.8016293.320871 Iteration: 13 bestvalit: 1.101356 bestmemit:1.5871302.605967 Is their any procedure to suppress this i.e not to print this information? Yes, the procedure is to read the help file, as you have been asked by the posting guide before posting. ?DEoptim points you to the help for ?DEoptim.control which has a trace argument that seems to be useful ... Uwe Ligges Thank you for your kind reply. Thanks& Regards Arnab Kumar Maity || IBM Global Process Services || || 2nd Floor, VBC Solitaire || || 47& 49, Bazullah Road || T Nagar || || Chennai - 600017 || India || || Email: arnab.ma...@dc.ibm.com || || Ph: +91 8939390048 || __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] converting a matrix or data.frame into an html table
On 9/05/2011 10:40 p.m., Samuel Le wrote: Dear all, Is there a function in R to convert a matrix or a data.frame into an html table? Many thanks, Samuel xtable() in the xtable package can do this (at least to some extent). It is commonly used to write LaTeX but there is an option to produce html as well. David Scott -- _ David Scott Department of Statistics The University of Auckland, PB 92019 Auckland 1142,NEW ZEALAND Phone: +64 9 923 5055, or +64 9 373 7599 ext 85055 Email: d.sc...@auckland.ac.nz, Fax: +64 9 373 7018 __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Suppressing iterations in DEoptim
Dear Uwe, Which help file you are talking about? Thanks & Regards Arnab Kumar Maity || IBM Global Process Services || || 2nd Floor, VBC Solitaire || || 47 & 49, Bazullah Road || T Nagar || || Chennai - 600017 || India || || Email: arnab.ma...@dc.ibm.com || || Ph: +91 8939390048 || Uwe Ligges To arnab.ma...@dc.ibm.com 05/09/2011 04:24 cc PMr-help@r-project.org Subject Re: [R] Suppressing iterations in DEoptim On 09.05.2011 11:06, arnab.ma...@dc.ibm.com wrote: > > Dear R users, > > During the the running of DEoptim function which belongs to "DEoptim" > package it automatically gives the output like the following: > > Iteration: 1 bestvalit: 181.379847 bestmemit:0.2264991.395852 > Iteration: 2 bestvalit: 14.062649 bestmemit:2.2903575.597838 > Iteration: 3 bestvalit: 14.062649 bestmemit:2.2903575.597838 > Iteration: 4 bestvalit: 14.062649 bestmemit:2.2903575.597838 > Iteration: 5 bestvalit: 14.062649 bestmemit:2.2903575.597838 > Iteration: 6 bestvalit: 14.062649 bestmemit:2.2903575.597838 > Iteration: 7 bestvalit: 14.062649 bestmemit:2.2903575.597838 > Iteration: 8 bestvalit: 12.952513 bestmemit:2.7157097.691444 > Iteration: 9 bestvalit: 3.254643 bestmemit:2.3901515.597838 > Iteration: 10 bestvalit: 3.254643 bestmemit:2.3901515.597838 > Iteration: 11 bestvalit: 1.820207 bestmemit:2.1707184.779070 > Iteration: 12 bestvalit: 1.205168 bestmemit:1.8016293.320871 > Iteration: 13 bestvalit: 1.101356 bestmemit:1.5871302.605967 > > Is their any procedure to suppress this i.e not to print this information? Yes, the procedure is to read the help file, as you have been asked by the posting guide before posting. ?DEoptim points you to the help for ?DEoptim.control which has a trace argument that seems to be useful ... Uwe Ligges > Thank you for your kind reply. > > > > Thanks& Regards > > Arnab Kumar Maity > > || IBM Global Process Services || > || 2nd Floor, VBC Solitaire || > || 47& 49, Bazullah Road || T Nagar || > || Chennai - 600017 || India || > || Email: arnab.ma...@dc.ibm.com || > || Ph: +91 8939390048 || > > __ > R-help@r-project.org mailing list > https://stat.ethz.ch/mailman/listinfo/r-help > PLEASE do read the posting guide http://www.R-project.org/posting-guide.html > and provide commented, minimal, self-contained, reproducible code. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] maximum likelihood convergence reproducing Anderson Blundell 1982 Econometrica R vs Stata
Hi Mike, Mike said "is this it, page 1559?" That is the front page yes, page 15*6*9 has the table, of which the model labelled 18s is the one I replicated. "did you actually cut/paste code anywhere and is your first coefficient -.19 or -.019? Presumably typos would be one possible problem." -0.19 is not a typo, it is pi10 in the paper, and a1 in my Stata estimation - as far as I can tell cutting and pasting is not the problem. "generally it helps if we could at least see the equations to check your code against typos ( note page number ?) in lnl that may fix part of the mystery. Is full text available on author's site, doesn't come up on citeseer AFAICT," Unfortunately I do not know of any place to get the full version of this paper that doesn't require access to a database such as JSTOR. The fact that this likelihood function reproduces the published results in Stata makes me confident that it is correct - I also have read a lot on systems estimation and it is a pretty standard likelihood function. "I guess one question would be " what is beta" in lnl supposed to be - it isn't used anywhere but I will also mentioned I'm not that familiar with the R code ( I'm trying to work through this to learn R and the optimizers). maybe some words would help, is sigma supposed to be 2x2 or 8x8 and what are e1 and e2 supposed to be?" The code above is certainly not as elegant as it could be - in this case the beta is rather superfluous. It is just a vector to hold parameters - but since I called all the parameters theta anyway there is no need for it. e1 and e2 are the residuals from the first and second equations of the system. Sigma is a 2x2 matrix which is the outer product of the two vectors of residuals. Kind regards, Alex On 9 May 2011 23:12, Mike Marchywka wrote: > > > > > > > >> Date: Mon, 9 May 2011 22:06:38 +1200 >> From: alex.ols...@gmail.com >> To: pda...@gmail.com >> CC: r-help@r-project.org; da...@otter-rsch.com >> Subject: Re: [R] maximum likelihood convergence reproducing Anderson >> Blundell 1982 Econometrica R vs Stata >> >> Peter said >> >> "Ahem! You might get us interested in your problem, but not to the >> level that we are going to install Stata and Tsp and actually dig out >> and study the scientific paper you are talking about. Please cite the >> results and explain the differences." >> >> Apologies Peter, will do, >> >> The results which I can emulate in Stata but not (yet) in R are reported >> below. > > did you actually cut/paste code anywhere and is your first coefficient -.19 > or -.019? > Presumably typos would be one possible problem. > >> They come from Econometrica Vol. 50, No. 6 (Nov., 1982), pp. 1569 > > > is this it, page 1559? > > http://www.jstor.org/pss/1913396 > > generally it helps if we could at least see the equations to check your > code against typos ( note page number ?) in lnl that may fix part of the > mystery. Is full text available > on author's site, doesn't come up on citeseer AFAICT, > > > http://citeseerx.ist.psu.edu/search?q=blundell+1982&sort=ascdate > > I guess one question would be " what is beta" in lnl supposed to be - > it isn't used anywhere but I will also mentioned I'm not that familiar > with the R code ( I'm trying to work through this to learn R and the > optimizers). > > maybe some words would help, is sigma supposed to be 2x2 or 8x8 and what are > e1 and e2 supposed to be? > > > > >> >> TABLE II - model 18s >> >> coef std err >> p10 -0.19 0.078 >> p11 0.220 0.019 >> p12 -0.148 0.021 >> p13 -0.072 >> p20 0.893 0.072 >> p21 -0.148 >> p22 0.050 0.035 >> p23 0.098 >> >> The results which I produced in Stata are reported below. >> I spent the last hour rewriting the code to reproduce this - since I >> am now at home and not at work :( >> My results are "identical" to those published. The estimates are for >> a 3 equation symmetrical singular system. >> I have not bothered to report symmetrical results and have backed out >> an extra estimate using adding up constraints. >> I have also backed out all standard errors using the delta method. >> >> . ereturn display >> -- >> | Coef. Std. Err. z P>|z| [95% Conf. Interval] >> -+ >> a | >> a1 | -.0188115 .0767759 -0.25 0.806 -.1692895 .1316664 >> a2 | .8926598 .0704068 12.68 0.000 .7546651 1.030655 >> a3 | .1261517 .0590193 2.14 0.033 .010476 .2418275 >> -+ >> g | >> g11 | .2199442 .0184075 11.95 0.000 .183866 .2560223 >> g12 | -.1476856 .0211982 -6.97 0.000 -.1892334 -.1061378 >> g13 | -.0722586 .0145154 -4.98 0.000 -.1007082 -.0438089 >> g22 | .0496865 .0348052 1.43 0.153 -.0185305 .1179034 >> g23 | .0979991 .0174397 5.62 0.000 .0638179 .1321803 >> g33 | -.0257405 .0113869 -2.26 0.024 -.0480584 -.0034226 >> ---
Re: [R] converting a matrix or data.frame into an html table
Have a look at hwrite() in the hwriter package:
http://www.embl.de/~gpau/hwriter/index.html
If x is a data frame, the following will do it:
> library("hwriter")
> hwrite(x, "x.html")
Cheers,
Greg
---
Gregoire Pau
EMBL Research Officer
http://www.embl.de/~gpau/
On 09/05/11 12:40, Samuel Le wrote:
Dear all,
Is there a function in R to convert a matrix or a data.frame into an html table?
Many thanks,
Samuel
[[alternative HTML version deleted]]
__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Re: [R] package update
On 08.05.2011 19:54, eric wrote: I tried to update my packages using update.packages() I got the following message: The downloaded packages are in ‘/tmp/RtmpyDYdTX/downloaded_packages’ Warning in install.packages(update[instlib == l, "Package"], l, contriburl = contriburl, : 'lib = "/usr/lib/R/library"' is not writable Error in install.packages(update[instlib == l, "Package"], l, contriburl = contriburl, : unable to install package How do I fix this ? If you want to update packages in R's default library in /usr/lib/R/library, you will need root permissions. Uwe Ligges -- View this message in context: http://r.789695.n4.nabble.com/package-update-tp3507479p3507479.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Suppressing iterations in DEoptim
On 09.05.2011 11:06, arnab.ma...@dc.ibm.com wrote: Dear R users, During the the running of DEoptim function which belongs to "DEoptim" package it automatically gives the output like the following: Iteration: 1 bestvalit: 181.379847 bestmemit:0.2264991.395852 Iteration: 2 bestvalit: 14.062649 bestmemit:2.2903575.597838 Iteration: 3 bestvalit: 14.062649 bestmemit:2.2903575.597838 Iteration: 4 bestvalit: 14.062649 bestmemit:2.2903575.597838 Iteration: 5 bestvalit: 14.062649 bestmemit:2.2903575.597838 Iteration: 6 bestvalit: 14.062649 bestmemit:2.2903575.597838 Iteration: 7 bestvalit: 14.062649 bestmemit:2.2903575.597838 Iteration: 8 bestvalit: 12.952513 bestmemit:2.7157097.691444 Iteration: 9 bestvalit: 3.254643 bestmemit:2.3901515.597838 Iteration: 10 bestvalit: 3.254643 bestmemit:2.3901515.597838 Iteration: 11 bestvalit: 1.820207 bestmemit:2.1707184.779070 Iteration: 12 bestvalit: 1.205168 bestmemit:1.8016293.320871 Iteration: 13 bestvalit: 1.101356 bestmemit:1.5871302.605967 Is their any procedure to suppress this i.e not to print this information? Yes, the procedure is to read the help file, as you have been asked by the posting guide before posting. ?DEoptim points you to the help for ?DEoptim.control which has a trace argument that seems to be useful ... Uwe Ligges Thank you for your kind reply. Thanks& Regards Arnab Kumar Maity || IBM Global Process Services || || 2nd Floor, VBC Solitaire || || 47& 49, Bazullah Road || T Nagar || || Chennai - 600017 || India || || Email: arnab.ma...@dc.ibm.com || || Ph: +91 8939390048 || __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] converting a matrix or data.frame into an html table
Hello, Samuel, take a look at the package R2HTML. Hth -- Gerrit On Mon, 9 May 2011, Samuel Le wrote: Dear all, Is there a function in R to convert a matrix or a data.frame into an html table? Many thanks, Samuel - Dr. Gerrit Eichner Mathematical Institute, Room 212 gerrit.eich...@math.uni-giessen.de Justus-Liebig-University Giessen Tel: +49-(0)641-99-32104 Arndtstr. 2, 35392 Giessen, Germany Fax: +49-(0)641-99-32109http://www.uni-giessen.de/cms/eichner __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Alter a line in a file.
On Thu, 05-May-2011 at 06:13AM -0700, Joel wrote:
|>
|> jholtman wrote:
|> >
|> > a <- readLines(textConnection('setting1="value1"
|> > setting2="value2"
|> > setting3="value3"
|> > setting4="value4"'))
|> > closeAllConnections()
|> > # change values
|> > ac <- sub('setting4="value4"', 'setting4="value5"', a)
|> > writeLines(ac, con='myFile.txt')
|> >
|>
|> Problem is that I dont know the value on all the settings that I wanna
|> change otherwise that looks like something to continue on.
|>
|>
|>
|> Petr Pikal wrote:
|> >
|> > What file, what is its structure, is it some R object or separate file?
|> > What did you try and what went wrong?
|> >
|> > Regards
|> > Petr
|> >
|>
|> Just a normal textfile nothing fancy
|> Ive tried diffrent kind of ways of useing my OS witch is linux by
|> the system command to do it for me but Im not good enought on
|> regexp to get it to work properly.
R is great for lots of things. I even use it for things that someone
more skilled would do using Perl, but in your case, it would be much
easier to use a text editor. If you can't use Emacs or vi, use nano.
You don't need to know anything about text editors to use the menu
options it has for everything.
HTH
--
~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.
___Patrick Connolly
{~._.~} Great minds discuss ideas
_( Y )_ Average minds discuss events
(:_~*~_:) Small minds discuss people
(_)-(_) . Eleanor Roosevelt
~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.
__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
[R] converting a matrix or data.frame into an html table
Dear all, Is there a function in R to convert a matrix or a data.frame into an html table? Many thanks, Samuel [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] maximum likelihood convergence reproducing Anderson Blundell 1982 Econometrica R vs Stata
Peter said "Ahem! You might get us interested in your problem, but not to the level that we are going to install Stata and Tsp and actually dig out and study the scientific paper you are talking about. Please cite the results and explain the differences." Apologies Peter, will do, The results which I can emulate in Stata but not (yet) in R are reported below. They come from Econometrica Vol. 50, No. 6 (Nov., 1982), pp. 1569 TABLE II - model 18s coef std err p10 -0.19 0.078 p11 0.2200.019 p12 -0.148 0.021 p13 -0.072 p20 0.8930.072 p21 -0.148 p22 0.0500.035 p23 0.098 The results which I produced in Stata are reported below. I spent the last hour rewriting the code to reproduce this - since I am now at home and not at work :( My results are "identical" to those published. The estimates are for a 3 equation symmetrical singular system. I have not bothered to report symmetrical results and have backed out an extra estimate using adding up constraints. I have also backed out all standard errors using the delta method. . ereturn display -- | Coef. Std. Err. zP>|z| [95% Conf. Interval] -+ a| a1 | -.0188115 .0767759-0.25 0.806-.1692895.1316664 a2 | .8926598 .070406812.68 0.000 .75466511.030655 a3 | .1261517 .0590193 2.14 0.033 .010476.2418275 -+ g| g11 | .2199442 .018407511.95 0.000 .183866.2560223 g12 | -.1476856 .0211982-6.97 0.000-.1892334 -.1061378 g13 | -.0722586 .0145154-4.98 0.000-.1007082 -.0438089 g22 | .0496865 .0348052 1.43 0.153-.0185305.1179034 g23 | .0979991 .0174397 5.62 0.000 .0638179.1321803 g33 | -.0257405 .0113869-2.26 0.024-.0480584 -.0034226 -- In R I cannot get results like this - I think it is probably to do with my inability at using the optimisers well. Any pointers would be appreciated. Peter said "Are we maximizing over the same parameter space? You say that the estimates from the paper gives a log-likelihood of 54.04, but the exact solution clocked in at 76.74, which in my book is rather larger." I meant +54.04 > -76.74. It is quite common to get positive log-likelihoods in these system estimation. Kind regards, Alex On 9 May 2011 19:04, peter dalgaard wrote: > > On May 9, 2011, at 06:07 , Alex Olssen wrote: > >> Thank you all for your input. >> >> Unfortunately my problem is not yet resolved. Before I respond to >> individual comments I make a clarification: >> >> In Stata, using the same likelihood function as above, I can reproduce >> EXACTLY (to 3 decimal places or more, which is exactly considering I >> am using different software) the results from model 8 of the paper. >> >> I take this as an indication that I am using the same likelihood >> function as the authors, and that it does indeed work. >> The reason I am trying to estimate the model in R is because while >> Stata reproduces model 8 perfectly it has convergence >> difficulties for some of the other models. >> >> Peter Dalgaard, >> >> "Better starting values would help. In this case, almost too good >> values are available: >> >> start <- c(coef(lm(y1~x1+x2+x3)), coef(lm(y2~x1+x2+x3))) >> >> which appears to be the _exact_ solution." >> >> Thanks for the suggestion. Using these starting values produces the >> exact estimate that Dave Fournier emailed me. >> If these are the exact solution then why did the author publish >> different answers which are completely reproducible in >> Stata and Tsp? > > > Ahem! You might get us interested in your problem, but not to the level that > we are going to install Stata and Tsp and actually dig out and study the > scientific paper you are talking about. Please cite the results and explain > the differences. > > Are we maximizing over the same parameter space? You say that the estimates > from the paper gives a log-likelihood of 54.04, but the exact solution > clocked in at 76.74, which in my book is rather larger. > > Confused > > -p > > >> >> Ravi, >> >> Thanks for introducing optimx to me, I am new to R. I completely >> agree that you can get higher log-likelihood values >> than what those obtained with optim and the starting values suggested >> by Peter. In fact, in Stata, when I reproduce >> the results of model 8 to more than 3 dp I get a log-likelihood of 54.039139. >> >> Furthermore if I estimate model 8 without symmetry imposed on the >> system I reproduce the Likelihood Ratio reported >> in the paper to 3 deci
[R] Rule based Classification
Dear R-help. I am studying Dataming using R and I am going to make Rule Based Classification's R code. But I searched for Rule Based Classification throught Google, I have failed to find out the package for R. Would you recommend R some packages which can make Rule Based Classification? Best Regards, Kyung Won Park __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] Suppressing iterations in DEoptim
Dear R users, During the the running of DEoptim function which belongs to "DEoptim" package it automatically gives the output like the following: Iteration: 1 bestvalit: 181.379847 bestmemit:0.2264991.395852 Iteration: 2 bestvalit: 14.062649 bestmemit:2.2903575.597838 Iteration: 3 bestvalit: 14.062649 bestmemit:2.2903575.597838 Iteration: 4 bestvalit: 14.062649 bestmemit:2.2903575.597838 Iteration: 5 bestvalit: 14.062649 bestmemit:2.2903575.597838 Iteration: 6 bestvalit: 14.062649 bestmemit:2.2903575.597838 Iteration: 7 bestvalit: 14.062649 bestmemit:2.2903575.597838 Iteration: 8 bestvalit: 12.952513 bestmemit:2.7157097.691444 Iteration: 9 bestvalit: 3.254643 bestmemit:2.3901515.597838 Iteration: 10 bestvalit: 3.254643 bestmemit:2.3901515.597838 Iteration: 11 bestvalit: 1.820207 bestmemit:2.1707184.779070 Iteration: 12 bestvalit: 1.205168 bestmemit:1.8016293.320871 Iteration: 13 bestvalit: 1.101356 bestmemit:1.5871302.605967 Is their any procedure to suppress this i.e not to print this information? Thank you for your kind reply. Thanks & Regards Arnab Kumar Maity || IBM Global Process Services || || 2nd Floor, VBC Solitaire || || 47 & 49, Bazullah Road || T Nagar || || Chennai - 600017 || India || || Email: arnab.ma...@dc.ibm.com || || Ph: +91 8939390048 || __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Summarising by group
On May 9, 2011, at 11:12 , Martyn Byng wrote:
> I wonder if someone with more experience than me on using R to summarise
> by group wants to post a reply to this
Not really (but how did those people manage to overlook by()?). However,
another matter
PLEASE DO NOT BE SO B***DY LAZY AND START A NEW TOPIC AS A REPLY TO SOMETHING
COMPLETELY UNRELATED.
Those of us with threading mail clients, will see your post as part of the
thread
"maximum likelihood convergence reproducing Anderson Blundell 1982 Econometrica
R vs Stata"
and, at least with Mac OSX's Mail, the header of the entire thread is now
"Summarising by group".
Peter D.
>
> http://www.analyticbridge.com/group/sasandstatisticalprogramming/forum/t
> opics/why-still-use-sas-with-a-lot
>
> To save everyone having to follow the link, the text is copied below
>
> "SAS has some nice features, such as the SQL procedure or simple "group
> by" features. Try to compute correlations "by group" in R: say you have
> 2,000 groups, 2 variables e.g. salary and education level, and 2 million
> observations - you want to compute correlation between salary and
> education within each group.
>
> It is not obvious, your best bet is to use some R package (see sample
> code on Analyticbridge to do it), and the solution is painful, you can
> not return both correlation and stdev "by group", as the function can
> return only one argument, not a vector. So if you want to return not
> just two, but say 100 metrics, it becomes a nightmare."
>
>
>
>
> The Numerical Algorithms Group Ltd is a company registered in England
> and Wales with company number 1249803. The registered office is:
> Wilkinson House, Jordan Hill Road, Oxford OX2 8DR, United Kingdom.
>
> This e-mail has been scanned for all viruses by Star. Th...{{dropped:4}}
>
> __
> R-help@r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.
--
Peter Dalgaard
Center for Statistics, Copenhagen Business School
Solbjerg Plads 3, 2000 Frederiksberg, Denmark
Phone: (+45)38153501
Email: pd@cbs.dk Priv: pda...@gmail.com
__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
