Re: [R] Intrduction of function

åæ wrote: Hi all: I've written a function and saved the worksapce.When the workspace of my function is re-open,I want display some introduction or step by step guidance of the function for the users.How can I do it? Thanks a lot! ??, you don't want to do distribute a workspace, but you want to cre

[R] SJava Issue

Hi, I have downloaded and installed SJava-0.68-0 on my linux box. When I try to initialise the JVM from within R this is what I get: > .JavaInit() (1) error initializing manager class can't find class java/lang/Hashtable Error in .JavaInit() : Couldn't start Java Virtual Machine: can't find cla

[R] can I get these result with R?

i want to check if the previously stock of social capital has impact on the present economoc performace.so i get the following variables:economic performace ,stock of socail capital ;each of them from year 1996 to 2002,from 30 different areas. the data as following: performance stockyear

Re: [R] "moving average" method for time series objects

Schwarz,Paul gartner.com> writes: : : Dear R-Help readers, : : I suspect that this question must be a FAQ, but my investigation of the archives has not been very revealing. : Is there an R function for calculating moving averages of time series objects? : : Thank you for your time and patie

Re: [R] folding table into a matrix

Gene Cutler amgen.com> writes: : : I'm just getting started with R, so feel free to point me to the : appropriate documentation if this is already answered somewhere (though : I've been unable to find it myself). This does seem like a rather : basic question. : I want to fold a table into a

[R] Intrduction of function

Hi all: I've written a function and saved the worksapce.When the workspace of my function is re-open,I want display some introduction or step by step guidance of the function for the users.How can I do it? Thanks a lot! My best regards! __ [EMAIL PRO

RE: [R] RMySQL and Blob

Hi, I tried your suggestion to blindly import the blob into R, doing the following: > con <- dbConnect("MySQL", host="host", user="user", dbname="db") > rs <- dbGetQuery(con, statement=paste("select picture from db where id=1") It didn't crash R. But rs is not usable. It seems that it has been c

[R] "moving average" method for time series objects

Dear R-Help readers, I suspect that this question must be a FAQ, but my investigation of the archives has not been very revealing. Is there an R function for calculating moving averages of time series objects? Thank you for your time and patience. -Paul Paul Schwarz, Ph.D. Associate Director

Re: [R] Cox proportional hazards model

Min-Han Tan wrote: Good afternoon, I am currently trying to do some work on survival analysis. - I hope to seek your advice re: 2 questions (1 general and 1 specific) (1) I'm trying to do a stratified Cox analysis and subsequently plot(survfit(object)). It seems to work for some strata, but not for

[R] decompose a correlation matrix

Thanks guys for the help, here's the final (grizzly?) solution: #generate a correlation matrix cm<-cor(someDataFrame, y = NULL ...) # get the list of labels (included in the dataframe) labels<-labels(cm)[[1]] # retrieve the uppper portion of the correlation matrix (as logical values) idx <- uppe

Re: [R] folding table into a matrix

Gene Cutler <[EMAIL PROTECTED]> writes: > I'm just getting started with R, so feel free to point me to the > appropriate documentation if this is already answered somewhere > (though I've been unable to find it myself). This does seem like a > rather basic question. > I want to fold a table into

Re: [R] Problems with boot and optim

Hi Luke, I think your problem is in the function lik.hetprobit and not remembering that R is case sensitive so X and x are not the same. The parameters passed in are called X, Y and Z which change for each bootstrap dataset. Within the function, however, your first three lines are Y <- as.matr

Re: [R] folding table into a matrix

Have you looked at "index arrays" in "An Introduction to R", available as the first menu option after "help.start()" in R? The version I got with R 1.9.1 for Windows includes the following: > x <- array(1:20,dim=c(4,5)) # Generate a 4 by 5 array. > x [,1] [,2] [,3] [,4]

[R] folding table into a matrix

I'm just getting started with R, so feel free to point me to the appropriate documentation if this is already answered somewhere (though I've been unable to find it myself). This does seem like a rather basic question. I want to fold a table into a matrix. The table is formatted like so: Colu

Re: [R] Issue with predict() for glm models

John Fox wrote: Dear Uwe, -Original Message- From: Uwe Ligges [mailto:[EMAIL PROTECTED] Sent: Thursday, September 23, 2004 11:37 AM To: John Fox Cc: [EMAIL PROTECTED] Subject: Re: [R] Issue with predict() for glm models . . . John, note that I used glm(y ~ .) (the dot!), because the n

RE: [R] decompose a correlation matrix

On 23-Sep-04 Mark Strivens wrote: > Is there a simple way to decompose the upper triangle > of a correlation matrix to a linear list; > > For example: > > X Y Z > X 1 2 3 > Y 2 1 4 > Z 3 4 1 > > so you get a list like: > > xy 2 > XZ 3 > YZ 4 > > I suspect you can do it with a matrix transfor

RE: [R] decompose a correlation matrix

> From: Mark Strivens > > Thanks for the answers the appear to be just > right. > > i.e. > > corrmat[upper.tri(corrmat)] > > or > > x[col(x)>row(x)] > > The slight problem is I lose all the column & > row labels from the correlation matrix, so I > am not sure of the order of the values (i

RE: [R] decompose a correlation matrix

> From: Duncan Murdoch > > On Thu, 23 Sep 2004 13:08:53 -0500, "Mark Strivens" > <[EMAIL PROTECTED]> wrote : > > >Is there a simple way to decompose the upper triangle > >of a correlation matrix to a linear list; > > > >For example: > > > > X Y Z > >X 1 2 3 > >Y 2 1 4 > >Z 3 4 1 > > > >so you ge

[R] decompose a correlation matrix

Thanks for the answers the appear to be just right. i.e. corrmat[upper.tri(corrmat)] or x[col(x)>row(x)] The slight problem is I lose all the column & row labels from the correlation matrix, so I am not sure of the order of the values (i.e. which combination of markers the value represent

RE: [R] decompose a correlation matrix

This may not have things in the order you want but you can see if it gets close to what you want: > x <- matrix(1:16,ncol=4) > x [,1] [,2] [,3] [,4] [1,]159 13 [2,]26 10 14 [3,]37 11 15 [4,]48 12 16 > y <- x[row(x) < col(x)] > y [1] 5 9 10 1

RE: [R] R glm

As ?glm says, see ?family. Andy > From: Kahra Hannu > > In Venables & Ripley: Modern Applied Statistics with S > (MASS), (4th edition), on page 184 there is a table "Families > and link functions" that gives you the available links with > different families. The default and the only link with

Re: [R] decompose a correlation matrix

On Thu, 23 Sep 2004 13:08:53 -0500, "Mark Strivens" <[EMAIL PROTECTED]> wrote : >Is there a simple way to decompose the upper triangle >of a correlation matrix to a linear list; > >For example: > > X Y Z >X 1 2 3 >Y 2 1 4 >Z 3 4 1 > >so you get a list like: > >xy 2 >XZ 3 >YZ 4 > >I suspect you ca

Re: [R] R vs EViews - serial correlation

The issue here is that you have confused an AR(1) process for the variable of interest with an AR(1) process for its residuals. The former is a true AR(1) process, while the latter is really an MA(1) process, in terms of Box-Jenkins style ARIMA models. Interpreting your original post: I met wi

[R] decompose a correlation matrix

Is there a simple way to decompose the upper triangle of a correlation matrix to a linear list; For example: X Y Z X 1 2 3 Y 2 1 4 Z 3 4 1 so you get a list like: xy 2 XZ 3 YZ 4 I suspect you can do it with a matrix transformation, but that beyond me at present. Many thanks Mark __

RE: [R] Issue with predict() for glm models

Dear Uwe, > -Original Message- > From: Uwe Ligges [mailto:[EMAIL PROTECTED] > Sent: Thursday, September 23, 2004 11:37 AM > To: John Fox > Cc: [EMAIL PROTECTED] > Subject: Re: [R] Issue with predict() for glm models > . . . > > John, > > note that I used glm(y ~ .) (the dot!), > beca

Re: [R] fitting weibull distribution

Hi. I think there may be one or more zeros in your data set, causing the problem: x <- rgamma(100) fitdistr(x, "weibull") fitdistr(c(x,0), "weibull") Maybe you should omit the zeros. Christian __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/ma

Re: followup: Re: [R] Issue with predict() for glm models

On Thu, 2004-09-23 at 12:02, Paul Johnson wrote: > I have a follow up question that fits with this thread. > > Can you force an overlaid plot showing predicted values to follow the > scaling of the axes of the plot over which it is laid? > > Here is an example based on linear regression, just fo

Re: [R] R glm

Upon examining Table 7.1 on page 184 of V&R 4th edition, I can see where the ambiguity would arise, however. Always best to check the help, I guess. Hank On Sep 23, 2004, at 1:04 PM, Paul Johnson wrote: No! > ?family The 'gaussian' family accepts the links '"identity"', '"log"' and '"

Re: [R] gsub

Thank you all for the help, specially Gabor that is exactly what I needed. A few examples that do the same thing is very helpful in understanding the structure of the call. Thank you again, Jean On Thu, 23 Sep 2004, Gabor Grothendieck wrote: > Jean Eid chass.utoronto.ca> writes: > > : > : H

RE: followup: Re: [R] Issue with predict() for glm models

Could you just use lines(newX, myPred, col=2) -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] Behalf Of Paul Johnson Sent: Thursday, September 23, 2004 10:3 AM To: r help Subject: followup: Re: [R] Issue with predict() for glm models I have a follow up question that

Re: [R] R glm

No! > ?family The 'gaussian' family accepts the links '"identity"', '"log"' and '"inverse"'; Kahra Hannu wrote: In Venables & Ripley: Modern Applied Statistics with S (MASS), (4th edition), on page 184 there is a table "Families and link functions" that gives you the available links wit

followup: Re: [R] Issue with predict() for glm models

I have a follow up question that fits with this thread. Can you force an overlaid plot showing predicted values to follow the scaling of the axes of the plot over which it is laid? Here is an example based on linear regression, just for clarity. I have followed the procedure described below to

Re: [R] block statistics with POSIX classes

Kahra Hannu mpsgr.it> writes: : : I have followed Gabor's instructions: : : > aggregate(list(y=y), list(dp$year), mean)$y # returns NULL since y is a time series : NULL : : > aggregate(list(y=as.vector(y)), list(dp$year), mean)$y # returns annual means : [1] 0

Re: [R] R glm

Dear Shuangge - There exists a default link function for each family, but you can specify the link, as well. see ?family (e.g., in html help click on the "family" link from the glm help page). Hank On Sep 23, 2004, at 12:25 PM, Shuangge Ma wrote: Hello: would you please help me with the followin

RE: [R] R glm

In Venables & Ripley: Modern Applied Statistics with S (MASS), (4th edition), on page 184 there is a table "Families and link functions" that gives you the available links with different families. The default and the only link with the gaussian family is identity. ciao, Hannu Kahra -Origin

Re: [R] Issue with predict() for glm models

John Fox wrote: Dear Uwe, -Original Message- From: Uwe Ligges [mailto:[EMAIL PROTECTED] Sent: Thursday, September 23, 2004 8:06 AM To: John Fox Cc: [EMAIL PROTECTED]; [EMAIL PROTECTED] Subject: Re: [R] Issue with predict() for glm models John Fox wrote: Dear Uwe, Unless I've somehow m

[R] fitting weibull distribution

Dear all, I get the following error message. And I cannot quite work out what is wrong. I think the optim gets infinite values. Certainly my data do not have any infinite values. How can I solve this? fitdistr(A1, "weibull") Error in optim(start, mylogfn, x = x, hessian = TRUE, ...) : non

Re: [R] Problem with R 1.9.1

Jacques Mendes Meyohas wrote: Hi, Could someone help me ? When I´m running the following command in the new R 1.9.1 version the error message appear. It didn´t happen on R 1.8.0 glm(indenizacao/sinistros ~ sexo + plano + faixa, family=Gamma(link="log"), weights=sinistros) Error in x[good, ] * w :

[R] R glm

Hello: would you please help me with the following glm question? for the R function glm, what I understand is: once you specify the "family", then the link function is fixed. My question is: is it possible I use, for example, "log" link function, but the estimation approach for the guassian famil

RE: [R] block statistics with POSIX classes

I have followed Gabor's instructions: > aggregate(list(y=y), list(dp$year), mean)$y # returns NULL since y > is a time series NULL > aggregate(list(y=as.vector(y)), list(dp$year), mean)$y# returns annual means [1] 0.0077656696 0.0224050294 0.001898 0.0240550925

RE: [R] detection of outliers

Not to oversimplify ... 1. (At least) dozens of books and thousands of papers have been written on this... 2. Most important question is: What is an outlier? (Many smart folks says that the concept is illogical/flawed -- there is no mystical boundary that one crosses to become a statistical paria

[R] detection of outliers

Hi, give a look to: http://www.itl.nist.gov/div898/handbook/eda/section3/eda35h.htm it's the Grubbs' Test for Outliers. It is based on the assumption of normality of data. Other methods of outliers' could: Run-Sequence Plot Histogram Normal Probability Plot Box-plot Best Vito you wrote: Hi

Re: [R] detection of outliers

On Thu, 23 Sep 2004 [EMAIL PROTECTED] wrote: > Hi, > this is both a statistical and a R question... > what would the best way / test to detect an outlier value among a series of 10 to 30 > values ? for instance if we have the following dataset: 10,11,12,15,20,22,25,30,500 > I d like to have a wa

[R] How to improve the quality of curve/line plots?

Dear list, I'm using the windows version of R. When plotting a curve or a line for time series with annual data , e. g. GDP growth 1991-2003, the line seems to exist of a lot of smaller lines. Printing the results the curves and lines seems to be "unclean" (because of using small resolution bit

Re: [R] Problem with R 1.9.1

On Thu, 23 Sep 2004 11:56:37 -0300, "Jacques Mendes Meyohas" <[EMAIL PROTECTED]> wrote : >Hi, > >Could someone help me ? >When I´m running the following command in the new R 1.9.1 version the error message >appear. It didn´t happen on R 1.8.0 > >> glm(indenizacao/sinistros ~ sexo + plano + faixa,

[R] R vs EViews - serial correlation

Dear all, I met with some problems when dealing with a time series with serial correlation. FIRST, I generate a series with correlated errors set.seed(1) x=1:50 y=x+arima.sim(n = 50, list(ar = c(0.47))) SECOND, I estimate three constants (a, b and rho) in the model Y=a+b*X+u, where u=rho*u(-1

[R] Gridbase basic question

All, I have a simple plot(x,y) and I would like to then insert rectangles of some length (in native coordinates) and height fixed to 0.5 in native coordinates. I can't quite get the code right to do this. Can anyone give me a quick example of how to do this? I looked the gridBase index a

Re: [R] detection of outliers

Hi Philippe, you could consider using the Windsorized mean, winds.mean <- function(x, k=2){ y <- x[!is.na(x)] mu <- mean(y) stdev <- sd(y) outliers.up <- y[y>mu+k*stdev] outliers.lo <- y[y y[y==outliers.up] <- mu+k*stdev y[y==outliers.lo] <- mu-k*stdev list(mean=sum(y)/leng

[R] Problem with R 1.9.1

Hi, Could someone help me ? When I´m running the following command in the new R 1.9.1 version the error message appear. It didn´t happen on R 1.8.0 > glm(indenizacao/sinistros ~ sexo + plano + faixa, family=Gamma(link="log"), > weights=sinistros) Error in x[good, ] * w : non-conformable arrays

Re: [R] detection of outliers

aol.com> writes: : : Hi, : this is both a statistical and a R question... : what would the best way / test to detect an outlier value among a series of 10 to 30 values ? for instance if we : have the following dataset: 10,11,12,15,20,22,25,30,500 I d like to have a way to identify the last da

RE: [R] Issue with predict() for glm models

Thanks to John Fox, Andy Liaw, and Uwe Ligges for their help with my problem regarding the use of the predict() function to obtain predictions for a new set of predictor values. It appears that the bottom line (at least for my purposes) is that the names and the setup for the data of the predicto

Re: [R] gsub

Jean Eid chass.utoronto.ca> writes: : : Hi : : A while back I used gsub to do the following : : temp<-"000US00231" : gsub("something here", "", temp) : "00231" : : I think it involved the `meta characters' somehow. : : I do not know how to do this anymore. I know strsplit will also work but

RE: [R] Issue with predict() for glm models

Dear Uwe, > -Original Message- > From: Uwe Ligges [mailto:[EMAIL PROTECTED] > Sent: Thursday, September 23, 2004 8:06 AM > To: John Fox > Cc: [EMAIL PROTECTED]; [EMAIL PROTECTED] > Subject: Re: [R] Issue with predict() for glm models > > John Fox wrote: > > > Dear Uwe, > > > > Unless

[R] detection of outliers

Hi, this is both a statistical and a R question... what would the best way / test to detect an outlier value among a series of 10 to 30 values ? for instance if we have the following dataset: 10,11,12,15,20,22,25,30,500 I d like to have a way to identify the last data as an outlier (only one dire

[R] nnet and weights: error analysis using V&R example

Dear R-users, dear Prof. Ripley as package maintainer I tried to investigate the odd error, when I call nnet together with a 'weights' parameter, using the 'fgl' example in V&R p 348 The error I get is: Error in eval(expr, envir, enclos) : Object "w" not found I think it is a kind of scop

Re: [R] gsub

You might want to look at ?regex. Sean On Sep 23, 2004, at 10:03 AM, Jean Eid wrote: Hi A while back I used gsub to do the following temp<-"000US00231" gsub("something here", "", temp) "00231" I think it involved the `meta characters' somehow. I do not know how to do this anymore. I know strsplit w

[R] gsub

Hi A while back I used gsub to do the following temp<-"000US00231" gsub("something here", "", temp) "00231" I think it involved the `meta characters' somehow. I do not know how to do this anymore. I know strsplit will also work but I remember gsub was much faster. In essence the question is ho

Re: [R] block statistics with POSIX classes

I am not sure that I understand what you are looking for since you did not provide any sample data with corresponding output to clarify your question. Here is another guess. If y is just a numeric vector with monthly data and dp is a POSIXlt vector of the same length then: aggregate(list(y=y

RE: [R] Issue with predict() for glm models

> -Original Message- > From: [EMAIL PROTECTED] > [mailto:[EMAIL PROTECTED] On Behalf Of John Fox > Sent: Thursday, September 23, 2004 8:49 AM > To: 'Uwe Ligges' > Cc: [EMAIL PROTECTED] > Subject: RE: [R] Issue with predict() for glm models > > > Dear Uwe, > > Unless I've somehow messe

Re: [R] Issue with predict() for glm models

John Fox wrote: Dear Uwe, Unless I've somehow messed this up, as I mentioned yesterday, what you suggest doesn't seem to work when the predictor is a matrix. Here's a simplified example: X <- matrix(rnorm(200), 100, 2) y <- (X %*% c(1,2) + rnorm(100)) > 0 dat <- data.frame(y=y, X=X) mod <- glm(y ~

RE: [R] block statistics with POSIX classes

Thank you Petr and Gabor for the answers. They did not, however, solve my original problem. When I have a monthly time series y with a POSIX date variable dp, the most obvious way to compute e.g. the annual means is to use aggregate(y, 1, mean) that works with time series. However, I got stuck w

RE: [R] Issue with predict() for glm models

Dear Uwe, Unless I've somehow messed this up, as I mentioned yesterday, what you suggest doesn't seem to work when the predictor is a matrix. Here's a simplified example: > X <- matrix(rnorm(200), 100, 2) > y <- (X %*% c(1,2) + rnorm(100)) > 0 > dat <- data.frame(y=y, X=X) > mod <- glm(y ~ X, fam

[R] [Job Ad] Position at Merck Research Laboratories, NJ USA

Please direct *all* inquiries to Vladimir Svetnik, the hiring manager. His contact information is below. (Also, please accept my apologies, for cross-posting to those subscribed to both R-help and S-news, and for any offense since this is a repost I made of the same position month ago. That short

[R] FYI: DeveloperWorks News article on R

First of a 3 part series, apparently: http://www-106.ibm.com/developerworks/linux/library/l-r1/?ca=dgr-lnxw02aAre (Apologies if someone has already posted this link to R-help) Best Regards, Bill ---

Re: [R] ordered probit and cauchit

roger koenker wrote: What is the current state of the R-art for ordered probit models, and more esoterically is there any available R strategy for ordered cauchit models, i.e. ordered multinomial alternatives with a cauchy link function. MCMC is an option, obviously, but for a univariate latent

Re: [R] multinomial logistic regression

hi all, you could have look at the library(VGAM). http://www.stat.auckland.ac.nz/~yee/VGAM/ hope this helps P.BADY At 17:36 22/09/2004 -0700, array chip wrote: >Hi, how can I do multinomial logistic regression in R? >I think glm() can only handle binary response >variable, and polr() can on

[R] nnet with weights parameter: odd error

Dear R-users I use nnet for a classification (2 classes) problem. I use the code CVnn1, CVnn2 as described in V&R. The thing I changed to the code is: I define the (class) weight for each observation in each cv 'bag' and give the vector of weights as parameter of nnet(..weights = weight.vector

Re: [R] multinomial logistic regression

On 23 Sep 2004, at 01:36, array chip wrote: Hi, how can I do multinomial logistic regression in R? I think glm() can only handle binary response variable, and polr() can only handle ordinal response variable. how to do logistic regression with multinomial response variable? Perhaps multinom() in pa

Re: [R] block statistics with POSIX classes

Kahra Hannu mpsgr.it> writes: : : I have a monthly price index series x, the related return series y = diff(log (x)) and a POSIXlt date-time : variable dp. I would like to apply annual blocks to compute for example annual block maxima and mean of y. : : When studying the POSIX classes, in the

Re: [R] aparchFit()$fitted.value

...unfortunately I was suspicious of this. Could You give me some insight to obtain that values? Thanks a lot! Lisa __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org

Re: [R] Best device for printing quality

Hi! I would first check what kind of graphic format the article publisher of the article accepts. If ps/pdf is ok I would use ?postscript. Otherwise I would change the journal. /E *** REPLY SEPARATOR *** On 9/24/2004 at 11:12 AM javier garcia - CEBAS wrote: >>>Hi all; >>>Jus

[R] Best device for printing quality

Hi all; Just to ask you for your advise about what is the best way to get the best quality for graphics to be incorporated into a printed article (I'm mainly a Linux useR, but also use the windows R version) Thanks and best regards, Javier Garcia __

Re: [R] t test problem?

On Wednesday 22 September 2004 13:07, Ted Harding wrote: > On 22-Sep-04 kan Liu wrote: > > Hi, Many thanks for your helpful comments and suggestions. The attached > > are the data in both log10 scale and original scale. It would be very > > grateful if you could suggest which version of test should