Thanks for the insight Bert. The data I quoted are an example from a
book(so I've got actual answers to compare to), but for my ultimate
purpose (analytical method development) there would typically be 3-6
replicate readings from each of 4-6 runs, which is on a similar scale.
I'll look into
many thanks Felipe
I didn't know the melt function.
I'll have a close look at it.
Regards/Cordialement
Benoit Boulinguiez
-Message d'origine-
De : Felipe Carrillo [mailto:mazatlanmex...@yahoo.com]
Envoyé : mercredi 9 septembre 2009 20:40
À : r-help@r-project.org; Benoit
This is to announce a new package MLCM on CRAN.
The package provides functions for estimating perceptual scales
by maximum likelihood from data collected in a conjoint measurement
experiment. Data for conjoint measurement are typically collected
using a psychophysical procedure. The stimuli vary
I am sorry for asking this stupid question, but i have been running in
circles. I want to randomly generate a scaling point of between 1 and 10,
for say hundred entries, where the first 10% percent is has rates between
2 and 7, the next 15% 3 and 7, 20% between 3 and 9, 20% between 3 and 10,
Hi everyone,
I still couldn't get the diagram as I mentioned before. I try Grey and
Milton suggestion but
it confusing.
I hope anyone helped me.
Thanks in advance.
Regards,
Hema.
On Thu, Sep 3, 2009 at 11:39 PM, Greg Snow greg.s...@imail.org wrote:
The my.symbols and ms.polygon functions in
Hello all,
I have a problem and need your help.
I am going to draw two plots in one row and two columns by using
“par(mfrow=c(1,2))”, but I want to first draw the right plot and then draw
the left plot. Does anybody can show me how to do it please? Thanks in
advance.
Legen
--
View this
Abbas R. Ali wrote:
Hi
Facing error in loading dababase table. Folowing is my code:
library('RODBC')
channel = odbcConnect(dsn, , )
data1 = sqlQuery(channel, SELECT * FROM TABLE, as.is = TRUE)
odbcClose(channel)
The object data1 is there, you do not need to load it from a
. The links are: R Sources - Windows - base -
Previous Releases. The direct link is: http://cran.at.r-
project.org/bin/windows/base/old/
That should of course read R Binaries - Windows - base - Previous
Releases.
__
R-help@r-project.org
Hi,
I need my plot to occupy a thin strip-like area but the plot area in R is a
square so when I save it and reduce its height to a strip in my document the
font in the graph looks flattened. Is there someway i can do this in R
itself?..so that my plot is a strip but the font looks normal
--
At 22:13 09/09/2009, Abhishek Pratap wrote:
I did try ?paste and paste(a,b,separator=). same result
Your second example pastes three strings together. a b and ,
the third of which you have named separator which is not the same as sep.
Thanks,
-Abhi
On Wed, Sep 9, 2009 at 5:11 PM, milton
On Wed, 2009-09-09 at 02:33 -0700, FMH wrote:
Thank you for the hints, but how could i add the grid lines which have
numbers, representing the height of the volcano on the image.
Thank you
So I think this script is what you need
Brazilan.Pallete - colorRampPalette(c(green,yellow,
Dear Robert
Thank you very much for all the help, now i am enjoying working with all of you
as you make R look simple and interesting.
--- On Thu, 10/9/09, Robert Baer rb...@atsu.edu wrote:
From: Robert Baer rb...@atsu.edu
Subject: Re: [R] Help on percentage of random numbers for different
I think you can try this:
par(mfrow=c(1,2))
plot(1, type = 'n', axes = FALSE, xlab = '', ylab = '')
plot(1, type = 'n', axes = FALSE, xlab = '', ylab = '')
par(mfg = c(1, 2))
plot(rnorm(10))
On Thu, Sep 10, 2009 at 1:49 AM, legen lege...@gmail.com wrote:
Hello all,
I have a problem and
On 09/10/2009 08:10 PM, rajesh j wrote:
Hi,
I need my plot to occupy a thin strip-like area but the plot area in R is a
square so when I save it and reduce its height to a strip in my document the
font in the graph looks flattened. Is there someway i can do this in R
itself?..so that my plot is
Dear All
I like to develop an application using .NET and R. The front end would be
.NET and statistical analysis would be done in R in the back end. So I
want to integrate .NET(VB) with R without using any interface (e.g., R
(D)com) to control. Secondly, I like to use Rscript (by calling .R
Mark Knecht wrote (09.Sep.2009 at 10:43 -0700):
Sometimes it's the simple things...
Why doesn't this lag X$x by 3 and place it in X$x1? (i.e. - Na's in
the first 3 rows and then values showing up...)
The help page does talk about time series. If lag doesn't work on
data.frame columns then
I currently have a data frame with a Fund ID and NAV value. Is it possible
to order the data frame and move to separate columns in a new data frame or
matrix in R without using a for loop? I suppose I'd like to use a built in
function to make it faster because I will have around 60,000 entries
Dear Sir
Subject: - *Install rscproxy_1.3-1.tar.gz *
I am working in Windows system. I was try to install *rscproxy* package
in two way.
*1.* install.packages (rscproxy_1.3-1.tar.gz), It shows the Warning:
unable to access index for repository
Dear all,
I am having an issue with displaying the dates on a plot with two
ordinates (i.e. two differently scaled y-axes). Instead of dates
appearing on the x-axis I am instead seeing a string of numbers
(14460, 14465, 14470 and 14475).
example R code:
library(plotrix)
x.Left -
On 9/10/2009 8:40 AM, Amitava1 M wrote:
Dear All
I like to develop an application using .NET and R. The front end would be
.NET and statistical analysis would be done in R in the back end. So I
want to integrate .NET(VB) with R without using any interface (e.g., R
(D)com) to control.
On 9/10/2009 6:44 AM, wesley mathew wrote:
Dear Sir
Subject: - *Install rscproxy_1.3-1.tar.gz *
I am working in Windows system. I was try to install *rscproxy* package
in two way.
*1.* install.packages (rscproxy_1.3-1.tar.gz), It shows the Warning:
unable to access index for repository
On Wed, Sep 9, 2009 at 2:53 PM, Afshartous, David
dafshart...@med.miami.edu wrote:
All,
Below is an xyplot plot with multiple panels and a title produced via main:
library(lattic)
data.ex = data.frame(y = rnorm(10), t = rep(1:5, 2), group = rep(c(0,1),
each = 5))
xyplot(y ~ t |
System.Diagnostics.Process in .Net can launch any program
such as Rscript. If that is not enough of a pointer to get you
going you need to post to a .Net group since this really is
about .Net programming, not about R programming.
On Thu, Sep 10, 2009 at 8:40 AM, Amitava1 M amitava...@tcs.com
Hi,
I am looking to execute an R script from VB as below.
The script runs fine but the redirection doesnt seem to happen. The
redirection operator and the out file seem to be treated as arguments
to the R script. Is there a way to get the operator working
thanks, R
System.Diagnostics.Process
hello everyone,
i'm new to R, so i hope you dont mind a fairly basic R question. we're
using R to manipulate the results of SQL queries and create an HTML output.
I'm starting with a table that looks essentially like this:
NameField1 Field2
John value1 value2
Jane value3
Hi dear reader,
I've been searching the help-archive and found many topics with regard to
the use of combinations, but I can't seem to make sense out of the advice
given. So I posted my question here, my apologies that this has come up for
many times before.
Example data-set:
Group
Dear R list,
is it possible to force the intercept to assume the value of 0 (that is no
intercept) in gam from gam package?
Regards
--
Corrado Topi
Global Climate Change Biodiversity Indicators
Area 18,Department of Biology
University of York, York, YO10 5YW, UK
Phone: + 44 (0) 1904 328645,
Dear R list,
I just obtained a negative AIC for two models (-221.7E+4
and -230.2E+4). Is that normal?
Regards
--
Corrado Topi
Global Climate Change Biodiversity Indicators
Area 18,Department of Biology
University of York, York, YO10 5YW, UK
Phone: + 44 (0) 1904 328645, E-mail:
Rather than use par(mfro...) you should probably take a look at the alternative
layout approach. That allows you to give R a matrix (corresponding to panels
in the plot) containing the number of the plot to be placed in each panel.
It also allows unequal panel sizes.
See ?layout for details.
Dear R-users,
Version V2.0 of the package mice is now available on CRAN for Windows, Linux
and Apple users.
Multivariate Imputation by Chained Equations (MICE) is the name of software for
imputing incomplete multivariate data by Fully Conditional Specifcation (FCS).
MICE V1.0 appeared in the
On Thu, 2009-09-10 at 14:58 +0100, Corrado wrote:
Dear R list,
is it possible to force the intercept to assume the value of 0 (that is no
intercept) in gam from gam package?
Just like you would in lm or glm for example, by adding -1 to your
formula. ?gam suggests you look at ?lm to see
Hi,
I'm trying to set up a server which allows different users to use R
simultaneously. Is it possible in Windows?
I know that a LINUX Server is probably a better option, but I had already
created a GUI with Tcl/tk in Windows. So some of the events don't work in LINUX.
Thanks in advance,
On 9/10/2009 9:25 AM, H Rao wrote:
Hi,
I am looking to execute an R script from VB as below.
The script runs fine but the redirection doesnt seem to happen. The
redirection operator and the out file seem to be treated as arguments
to the R script. Is there a way to get the operator working
I'd like to fit a SARIMA model on a timeseries but the period I'd like to
use is too big (7 day in 15min samples = 672) for the algorithm used in R.
Some suggested alternatives?
Thanks,
Matteo Bertini
[[alternative HTML version deleted]]
__
#Example data
df - data.frame(trt = factor(c(A long label, Another long \n label)),
outcome = c(1,4))
#Install ggplot2 if needed
library(ggplot2)
p - ggplot(df, aes(y=outcome, x=trt))
p - p + geom_bar(position=dodge, stat=identity)
p - p + opts(axis.text.x = theme_text(angle = 45, hjust=1))
p
srpd TCLTK wrote:
Hi,
I'm trying to set up a server which allows different users to use R
simultaneously. Is it possible in Windows?
Yes, I guess you want to use some Terminal Server. As for any other
software, each user can start own instances of R.
Uwe Ligges
I know that a
On Thu, Sep 10, 2009 at 3:07 PM, srpd TCLTKsrpd2...@hotmail.com wrote:
Hi,
I'm trying to set up a server which allows different users to use R
simultaneously. Is it possible in Windows?
I know that a LINUX Server is probably a better option, but I had already
created a GUI with Tcl/tk
Corrado-5 wrote:
Dear R list,
I just obtained a negative AIC for two models (-221.7E+4
and -230.2E+4). Is that normal?
It's not necessarily wrong. See http://emdbolker.wikidot.com/faq
--
View this message in context:
http://www.nabble.com/Negative-AIC-tp25383791p25384865.html
One could probably use one of the apply family of functions (apply,
lapply, sapply), but having looked into it a bit, I think it's
simpler to use an explicit loop. I doubt you'll encounter a need for
greater efficiency, in the cpu time sense, unless your tables are
huge.
But the looping can
My worry is: can I compare negative AIC with positive AIC? does the comparison
still hold?
On Thursday 10 September 2009 15:57:01 Ben Bolker wrote:
Corrado-5 wrote:
Dear R list,
I just obtained a negative AIC for two models (-221.7E+4
and -230.2E+4). Is that normal?
It's not
Hello everyone,
My problem is better explained with an example:
x=data.frame(a=1:4,b=1:4,c=rnorm(4))
x
a b c
1 1 1 -0.8821089
2 2 2 -0.7082583
3 3 3 -0.5948835
4 4 4 -1.8571443
y=data.frame(a=c(1,3),b=3,c=rnorm(2))
y
a bc
1 1 3 -0.273155973
2 3 3 0.009517862
Now I
Try downloading the rscproxy-.ZIP file on windows. Extension tar.gz
is used (mostly) on linux
or
install.packages('rscproxy')
-c
wesley mathew wrote:
Dear Sir
Subject: - *Install rscproxy_1.3-1.tar.gz *
I am working in Windows system. I was try to install *rscproxy* package
in
If all the models are fitted to the same data set, using the same
modeling tools (you have to be careful e.g. comparing lmer models to
glm models, because they use different additive constants), and
everything seems to make sense (!!!), then yes. I would be a little
surprised, and think that
Hi,
yes the AIC can be negative. To choose the model we use the criteria of
lower AIC (-230.2E+4).
Murilo Doi
Corrado-5 wrote:
Dear R list,
I just obtained a negative AIC for two models (-221.7E+4
and -230.2E+4). Is that normal?
Regards
--
Corrado Topi
Global Climate Change
Try representing the pentagon as a set of complex
numbers. Translate them by adding a complex
number and multiply by exp(1i*angle) to rotate them
around the origin. E.g. to rotate them around their
center of gravity, mean(p), do
p-complex(real=c(4,5,7,8,6), imag=c(5,3,3,5,7))
plot(p,
Enders (2004), Applied Econometric time series, Wiley, Exercise 10,
page 102, sets out some of the variations of the AIC and SBC and
contains a good definition. As these are all monotonic
transformations of one another they lead to the same maximum
(minimum). I say maximum/minimum because I
I think you could use reshape and ascii package here.
Create a file (code.Rnw) with this code :
John and Jane
=
=
df - data.frame(names = c(John, Jane), field1 = c(value1, value2),
field2 = c(value3, value4))
library(reshape)
cdf - cast(melt(df, id = names), variable ~ . | names)
@
Try this:
xy - merge(x, y, by = c(a,b),all = TRUE)
xy$c - ifelse(rowSums(!is.na(.x - xy[, c('c.x', 'c.y')])) 1, .x[,1],
rowSums(.x, na.rm = TRUE))
xy
On Thu, Sep 10, 2009 at 12:21 PM, JiHO jo.li...@gmail.com wrote:
Hello everyone,
My problem is better explained with an example:
I think the problem is trying to compare different models trained don the same
dataset.
1) If I compare for example gam (from gam package) with and without intercept,
is that a valid comparison?
For example: model with intercept has explained dev 24%, with AIC -2217146,
model without
Dear Kingsford,
I apologise for breaking the thread, but I thought there were some more people
who would be interested.
What you propose is what I am using at the moment: the sum of the squares of
the residuals, plus variance / stdev. I am not really satisfied. I have also
tried using R2,
'Layout' is the way to go. You can define a layout as:
LO - layout(matrix(c(1, 2, 3, 4), ncol=2))
In your case, you would probably want to use:
layout(matrix(c(2, 1), ncol=2))
Then, the first plot will be drawn in space number 2, and then the
second plot will be drawn in space number 1.
Hope
Hi, All,
How can I get the indices of the minimum elements in a matrix without using
a loop?
For example, if the matrix is
4 5 2
2 8 9
5 2 3
Then I want to output (1,3), (2,1), (3,2).
Thanks,
Annie
[[alternative HTML version deleted]]
__
Try this:
m - rbind(c(4,5,2), c(2,8,9), c(5,2,3))
cbind(1:NROW(m), apply(m, 1, which.min))
On Thu, Sep 10, 2009 at 3:34 PM, annie Zhang annie.zhang2...@gmail.comwrote:
Hi, All,
How can I get the indices of the minimum elements in a matrix without using
a loop?
For example, if the matrix
On Sep 10, 2009, at 1:34 PM, annie Zhang wrote:
Hi, All,
How can I get the indices of the minimum elements in a matrix
without using
a loop?
For example, if the matrix is
4 5 2
2 8 9
5 2 3
Then I want to output (1,3), (2,1), (3,2).
Thanks,
Annie
mat - matrix(c(4, 2, 5, 5, 8, 2, 2,
Thanks for all your help. Yes, it's very helpful.
Annie
On Thu, Sep 10, 2009 at 11:42 AM, Marc Schwartz marc_schwa...@me.comwrote:
On Sep 10, 2009, at 1:34 PM, annie Zhang wrote:
Hi, All,
How can I get the indices of the minimum elements in a matrix without
using
a loop?
For example,
Try the following:
Data - read.table('Sample.txt', header=T)
Data
IDUNAV
1 1694 999.89
2 1696 999.90
3 1694 999.87
4 1696 999.88
5 1694 999.84
6 1696 999.86
7 1694 999.82
8 1696 999.84
9 1694 999.79
10 1696 999.82
11 1694 999.71
12 1696 999.75
13 1694 999.69
14
Hi,
I am trying to solve this equation prob = exp(-3.33 + 0.0102*x)/(1+exp(-3.33 +
0.0102*x)). I want to write a function where I call the function and enter the
'prob' value and the output should be the 'x'. Im not sure how to write this. I
have a basic structure but im not sure if its
Hi Benoit,
I'm not a specialist of ggplot2, but I will try to help.
You may obtain more --interesting-- answers on the ggplot2
mailing list. This said, let's go.
To solve your problem, I would suggest to
1. change the form of the data frame (using the reshape library)
in order to have one
You don't need an equation solver. This is basic algebra.
The solution is:
X = (log(prob) - log(1 - prob) + 3.33) / 0.0102
Ravi.
---
Ravi Varadhan, Ph.D.
Assistant Professor, The Center on Aging and Health
Me:
Win XP
4 gig ram
R 2.9.2
library(foreign) # to read/write SPSS files
library(doBy) # for summaryBy
library(RODBC)
setwd(C:\\Documents and Settings\\00909BR)
gc()
memory.limit(size=4000)
## PROBLEM:
I have memory limit problems. R and otherwise. My dataframes for
merging or
For my Redhat 5.2 Linux box, which version of R would be most stable?
I am doing forecasting, statistics, etc.
Thanks!
Steve
__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide
Hi,
On Sep 10, 2009, at 4:47 PM, S. Few wrote:
For my Redhat 5.2 Linux box, which version of R would be most stable?
I am doing forecasting, statistics, etc.
I believe the conventional wisdom is to always download the latest
version ... and also, typically, update your current version to
On Sep 10, 2009, at 4:33 PM, Steve Lianoglou wrote:
Hi,
On Sep 10, 2009, at 4:47 PM, S. Few wrote:
For my Redhat 5.2 Linux box, which version of R would be most stable?
I am doing forecasting, statistics, etc.
I believe the conventional wisdom is to always download the latest
version
Hi r-users,
Can I do a numerical integration in R to solve for F(z)- integral_0^z {f(t) dt}
= 0 where F(z) is the CDF and f(t) is the pdf? What package can I use?
Thank you so much for any help given.
[[alternative HTML version deleted]]
My goodness! Did you try ?integrate ?
Bert Gunter
Genentech Nonclinical Biostatistics
-Original Message-
From: r-help-boun...@r-project.org [mailto:r-help-boun...@r-project.org] On
Behalf Of Roslina Zakaria
Sent: Thursday, September 10, 2009 3:36 PM
To: r-help@r-project.org
Subject:
Hi,
I need to do some binning which to date I've done just writing
subset commands. I'm now wondering if there are any good packages that
have some good pre-designed functions for multi-variable binning using
say 4 or 5 variables, sometimes binning on 3 or more levels of each
variable, and then
That will not work (or at least doesn't work for me.
This does work:
fnam-'thefilename.csv' #or build the name however you like
fpath - 'macintoshhd/users/me/myfolder/ # or whatever you need
read.csv(eval(paste(fpath,fnam,sep=)) #worked for me
Carl
---
Try this:
In the plot below, there are some grid cells that have values below 10, which
is the lowest cut value I have specified. Is there a way, without
adjusting the number of cuts, to tell R to fill in those cells with the
lowest possible color (in this case greeen)? There is a white hole in the
image
packages:
plyr
reshape (the package, not the base R function)
There may well be others...
Bert Gunter
Genentech Nonclinical Biostatistics
-Original Message-
From: r-help-boun...@r-project.org [mailto:r-help-boun...@r-project.org] On
Behalf Of Mark Knecht
Sent: Thursday, September 10,
-Original Message-
From: r-help-boun...@r-project.org
[mailto:r-help-boun...@r-project.org] On Behalf Of S. Few
Sent: Thursday, September 10, 2009 1:46 PM
To: r-help@r-project.org
Subject: [R] R 2.9.2 memory max - object vector size
Me:
Win XP
4 gig ram
R 2.9.2
Oh strange, as it worked for me..
Thanks for providing alternative method in solving the problem!
On Fri, Sep 11, 2009 at 9:01 AM, Carl Witthoft c...@witthoft.com wrote:
That will not work (or at least doesn't work for me.
This does work:
fnam-'thefilename.csv' #or build the name however
Thanks Bert,
I've used reshape a bit but hadn't considered it for this need.
plyr is new to me so I'll check it out.
I think the hard part in my case is designing the bins. I have some
continuous signals for which I don't know how many bins I want to
break each into. I'd like to be able to
Hi,
I have Win XP 32, 4 gig DDR2 and R 2.9.2.
I have memory limit problems.
memory.limit(4090)
[1] 4090
memory.limit()
[1] 4090
a-trans.matrix.f(7) # made big matrix of integer 16384*16384
Error: cannot allocate vector of size 512.0 Mb
I not have other objects in R memory.
what I do?
Hi,
On Thu, Sep 10, 2009 at 8:24 PM, oleg portnoyoleg.portno...@gmail.com wrote:
Hi,
I have Win XP 32, 4 gig DDR2 and R 2.9.2.
I have memory limit problems.
memory.limit(4090)
[1] 4090
memory.limit()
[1] 4090
a-trans.matrix.f(7) # made big matrix of integer 16384*16384
Error: cannot
I'm at my wit's end, and have searched all of my sources. I need to generate
a relatively large number of individual LOESS fits each month of data (I
have about 16 months of data). Fitting the polynomial is not my problem,
figuring out what the formula that describes that polynomial is. apologies
Hi listers,
I would like a suggestion. I am working on a bootstrap simulation which I am
calculation the confidence intervals to obtain the coverage probability. I
am applying 3 kind of confidence intervals and 3 coverage probabilities (2
sided, left 5% and left 95%).
I programmed a function for
Tena koe
Loess uses local fitting: Fitting is done locally. That is, for the
fit at point x, the fit is made using points in a neighbourhood of x,
weighted by their distance from x (from the help). That is, there is
no single formula to describe the fit.
HTH
Peter Alspach
-Original
Alternatives to sprintf() include formatC() or
prettyNum(), which would have to be used in
combination with paste().
In Carl's solution, the file.path() function
should be considered, since it automatically uses
the correct path separators for the OS.
Furthermore, eval() is not necessary.
Hello,
Does anyone know anything about using R to fit stated preference
econometric data using multinomial logit? I am not sure that standard
VGLM/VGAM can handle this, or if it does, how. This data is different
than more typical revealed preference data in that it is recorded as in
the
Hi
My suggested code had dropped the ...
format=epswrite
... and if you put that back, then the /setpagesize command is removed.
Does that improve things in your test cases?
Paul
Ted Harding wrote:
Thanks, Paul.
In fact I had been hoping to lure you to the surface, from the
12740-km
Martin Maechler maech...@stat.math.ethz.ch [Wed, Sep 02, 2009 at 09:17:42AM
CEST]:
PaCo == p connolly p_conno...@slingshot.co.nz
on Wed, 02 Sep 2009 12:19:31 +1200 writes:
PaCo On Mon, 31-Aug-2009 at 08:25PM +1000, Jim Lemon wrote:
PaCo [...]
[...]
PaCo | Emacs still
Dear R users,
I would like to accumulate objects generated from 'for' loop to a list or
array.
To illustrate the problem, arbitrary data set and script is shown below,
x - data.frame(a = c(rep(n,3),rep(y,2),rep(n,3),rep(y,2)), b =
c(rep(y,2),rep(n,4),rep(y,3),n), c = c(rep(n,7),rep(y,3)), d =
82 matches
Mail list logo