RE: [R] Problem in random (lme)

I use lme like this : lme(yield~hm*variety,data=donnees,random=~grandrep/hm+rep+block%in%rep) and I get this message : Error in getGroups.data.frame(dataMix, groups) : Invalid formula for groups Thanks Liaw, Andy [EMAIL PROTECTED] wrote: Springer is currently having a Statistics

Re: [R] advanced dist

Martin Klaffenboeck wrote: Hi there. I have now found that dist() does what I want in a specific case. But I have (out of many fields) in my Fragebogen.data file: VpnCodeFamilyTest 1X1m45 2X1t58 3X2m44 4X2t43 ... When I now do: Fbg -

Re: [R] WinMenu's question

Ross Darnell wrote: I am using the Windows menu functions below which will work on the first pass, but if I repeat the same script I cannot get the WinMenuAddItem to work. This is a problem if I change the menu structure and reread the source code I am forced to quit and restart Rgui. try.menu -

[R] S4 classes?

The following example, extracted from pp. 38-42 of Chambers (1998) Programming with Data (Springer), works for me in S-Plus 6.2 but not R 1.9.0pat, which returns the indicated error messages: setClass('track', representation(x=numeric, y=numeric)) [1] track tr1 - new(track, x=1:3,

Re: [R] S4 classes?

Spencer == Spencer Graves [EMAIL PROTECTED] on Wed, 02 Jun 2004 01:32:17 -0700 writes: Spencer The following example, extracted from pp. 38-42 of Chambers (1998) Spencer Programming with Data (Springer), works for me in S-Plus 6.2 but not R Spencer 1.9.0pat, which returns the

Re: [R] S4 classes?

Dear Spencer, I do not encounter any problem running your code in my machine. Maybe is something wrong with your R installation! setClass('track', representation(x=numeric, y=numeric)) tr1 - new(track, x=1:3, y=4:6) plot.track - function(x, y, ...){ plot([EMAIL PROTECTED], [EMAIL PROTECTED],

[R] ARCH-M, EGARCH

Hi, I would like to know if there are R packages in order to fit ARIMA models with ARCH-M and EGARCH variance specifications. I know packages tseries, stats, nlme where I found functions : arima.sim, arima, garch. But it's not enough for me. I need to study ARCH-m and EGARCH. Thank you very much

Re: [R] Making a ranking algorithm more efficient

let's start by defining x and y matching the properties of the points in the picture *= x-c(1,2,4,5,9,3,7,6); y-c(10,8,5,3,2,9,4,7) plot(x,y,pch=letters[1:8]) @ along each dimension we have to compare the coordinates of the points: *= outer(x,x,) @ we get a logical matrix: output-start Wed Jun

[R] autokorrelationresistente Kovarianz in R und S-plus

Liebes r-help-Team, ich bin gerade an meiner NDK-Abschlussarbeit und wollte anfragen, ob Sie wissen, ob R und S-plus eine Kovarianz für robuste MM-Schätzer zur Verfügung stellen, die gegen Autokorrelation resistent ist. Können Sie mir da weiterhelfen? Vielen Dank, Carsten Colombier Dr.

Re: [R] autokorrelationresistente Kovarianz in R und S-plus

Carsten, the language on this list is English. On Wed, 2 Jun 2004 11:17:04 +0200 [EMAIL PROTECTED] wrote: Liebes r-help-Team, ich bin gerade an meiner NDK-Abschlussarbeit und wollte anfragen, ob Sie wissen, ob R und S-plus eine Kovarianz für robuste MM-Schätzer zur Verfügung stellen,

Re: [R] S4 classes?

Spencer Graves wrote: The following example, extracted from pp. 38-42 of Chambers (1998) Programming with Data (Springer), works for me in S-Plus 6.2 but not R 1.9.0pat, which returns the indicated error messages: setClass('track', representation(x=numeric, y=numeric)) [1] track tr1 -

[R] poisson regression with robust error variance ('eyestudy')

Dear all, i am trying to redo the 'eyestudy' analysis presented on the site http://www.ats.ucla.edu/stat/stata/faq/relative_risk.htm with R (1.9.0), with special interest in the section on relative risk estimation by poisson regression with robust error variance. so i guess rlm is the function

Re: [R] Parametric Curves

See also the scatterplot3d package. Hank On Jun 1, 2004, at 10:01 AM, Talita Leite wrote: Hi everybody! I'm trying to plot a parametric curve (three dimensions) using R but I didn't obtain good results. Somebody have already done something like that? Please help me! Talita Perciano Costa Leite

RE: [R] Contrasts

Try the fit.contrast() and estimable() functions from my gregmisc package, or the contrasts() function in Frank Harrell's Design package. -Greg -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] Behalf Of Kimberly Ann Fernandes Sent: Monday, May 31, 2004 1:10 PM

[R] methods for complex sample surveys

I have learned a lot from this list. I would like to thank the developers and contributors who devote so much of their time to this project. Does anyone know if any methods have been developed for handling data from complex sample surveys that include sample weights, clusters, strata, and so on?

Re: [R] methods for complex sample surveys

[EMAIL PROTECTED] wrote on 02/06/2004 15:21:14: I have learned a lot from this list. I would like to thank the developers and contributors who devote so much of their time to this project. Does anyone know if any methods have been developed for handling data from complex sample surveys

[R] Virus intercepted

A message you sent to [EMAIL PROTECTED] contained Worm.SomeFool.Gen-1 and has not been delivered. __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide!

[R] How to iterate through two objects of class list fast?

Hi! I have 2 list objects One list contains the data (list1) the second list2 contains the e.g linear model for each element of list 1. list2 - lapply(list1,mylm,response) I obtain list 2 by something like this. now I have a function myfunc which takes an element from list1 and the

Re: [R] ffnet problem

On Tuesday 01 June 2004 12:24, Adrian Trapletti wrote: Given that those files are dated 27/06/2000, they are unlikely to work with the current version of R. (R has changed quite a bit since 2000!!) In fact, I stopped to support ffnet in 2000, and I would be very surprised if it would still

[R] use of split.screen() with postscript device

Greetings, I am new to R and quite confused by the apparent inconsistency in it's behavior. My latest difficulty lies in producing eps output for use with latex. In particular, I was successful in obtaining a single figure by using: postscript(ripple1.eps,onefile=FALSE)

Re: [R] How to iterate through two objects of class list fast?

Wolski [EMAIL PROTECTED] writes: list3[[x]] - myfunc(list1[[x]],list2[[x]]) Until now I am runnign this in a for(x in 1:length(list1)) loop. But for loops are slow especially if list3 is HUGE. What can I do? Use mapply(). I wouldn't expect the for loop to be all that slow unless you

Re: [R] poisson regression with robust error variance ('eyestudy')

On Wed, 2 Jun 2004, Lutz Ph. Breitling wrote: Dear all, i am trying to redo the 'eyestudy' analysis presented on the site http://www.ats.ucla.edu/stat/stata/faq/relative_risk.htm with R (1.9.0), with special interest in the section on relative risk estimation by poisson regression with

Re: [R] methods for complex sample surveys

On Wed, 2 Jun 2004, Paul E. Green wrote: I have learned a lot from this list. I would like to thank the developers and contributors who devote so much of their time to this project. Does anyone know if any methods have been developed for handling data from complex sample surveys that

Re: [R] How to iterate through two objects of class list fast?

Hallo! Hi I was checking the performance of the for loop and mapply with system.time() Case a) the result list is allocated. It is the same list which element i pass as an argument. e.g. list2[[x]] - myfunc(list2[[x]],list3[[x]]) 24.18 s Case b) the same with mapply(myfunc,list2,list3) 1.96 s

Re: [R] Manova and contrasts

Dear Eduardo, Hi R-users I'm trying to do multivariate analysis of variance of a experiment with 3 treatments, 2 variables and 5 replicates. The procedure adopted in SAS is as follow, but I'm having difficulty in to implement the contrasts for comparison of all treatments in R. [See the original

Re: [R] poisson regression with robust error variance ('eyestudy')

Thomas Lumley wrote: On Wed, 2 Jun 2004, Lutz Ph. Breitling wrote: Dear all, i am trying to redo the 'eyestudy' analysis presented on the site http://www.ats.ucla.edu/stat/stata/faq/relative_risk.htm with R (1.9.0), with special interest in the section on relative risk estimation by poisson

Re: [R] advanced dist

Am 02.06.2004 10:13:49 schrieb(en) Peter Wolf: what about: mtdist- as.matrix(dist(Fbg['Test'])) dimnames(mtdist) - list( Fbg[ 'Family' ], Fbg[ 'Family' ] ) mtdist [ Fbg['Code']==m ,Fbg['Code']==t ] Thanks, thats really what I want. I hope I can do that by myself, soon. Martin

[R] What's the Edgeworth expansion of a random vector

Dear R users, I have a statistical question regarding on the Edgeworth expansion of a random vector. Assume x is a d-dimensional random vector, and whats the expression of its Edgeworth expansion up to order 4? I only get the formulation for a scalar random variable. So anyone can help me out

[R] How do i draw a step function using R?

__ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html

[R] How do I prevent google search to post my questions asked here??

__ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html

[R] Request comments on missing data diagnosis code

Greetings, The attached code is my preliminary attempt to create a comprehensive missing data diagnostic package. I would greatly appreciate any constructive feedback about the code and encourage others to use it if they feel it is helpful. One warning might be in order - I have tested the

Re: [R] How do i draw a step function using R?

Hi John! Was you trying to use help.search(stepfunc) Sincerely Eryk *** REPLY SEPARATOR *** On 6/2/2004 at 6:48 PM john miller wrote: __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help PLEASE do

[R] data filtering

I would like to know if there is a way to do the following command in one step, primarily for speed on large data (5 million elements), and secondarily for readablity. mean(delta[(intersect(which(x[['class']]==0),which(delta1)))]) Do I really have to rely on an intersect operator? Isn't that

[R] factor - numeric

Hi, I'm extracting data from a database with values for different observation types in the same variable (another variable deifnes the observation type). Some of these observation types are factors, so R naturally classifies the entire variable as a factor. I want to select a subset and convert

Re: [R] data filtering

I think you want to use a single `' rather than a double `'. -roger HENRIKSON, JEFFREY wrote: I would like to know if there is a way to do the following command in one step, primarily for speed on large data (5 million elements), and secondarily for readablity.

Re: [R] factor - numeric

Have you tried as.numeric(as.character(rsm2$Value))? The construct as.numeric(rsm2$Value) returns the NUMERIC CODES for the different levels; as.character(rsm2$Value) returns the character representation, which you can then convert to numeric. hope this helps. spencer graves

[R] Distributed computing with R

Dear all, We have started using R for data analysis since a few months and find it useful. We are planning to acquire a high-end dedicated system for microarray data analysis and thinking of a distributed environment. I would appreciate if some one could send some pointers regarding how to choose

RE: [R] Distributed computing with R

Soraj, Haven't had any experience with R in a distributed computing environment, but have used Condor (http://www.cs.wisc.edu/condor/) with several applications. It's free, has a public license for use, is easy to use, but is not open source. Since you can batch up R code, this might be a

[R] Using postscript() in a script that is source()ed

I have a script that draws 9 graphics which I would like to run by source()ing the file. In the script I make objects that contain each of the graphics (all lattice objects or functions that contain lattice functions). Then at the end of the script, I have a section which prints them to

Re: [R] swapping with data.frame

Eryk == Eryk Wolski [EMAIL PROTECTED] on Tue, 01 Jun 2004 20:03:03 +0200 writes: Eryk Hi! U can use. Eryk rbind(t1,t2,t3) yes, but not for getting a data frame! nor does give as.data.frame( rbind(t1,t2,t3) ) give the correct result {make use of str(.) to see this quickly}

Re: [R] How do I prevent google search to post my questions asked here??

john == john miller [EMAIL PROTECTED] on Wed, 02 Jun 2004 18:55:01 + writes: (everything in the subject): john How do I prevent google search to post my questions john asked here?? you don't: R-help is famous and celebrity can't be gotten rid off ;-) Regards, Martin

Re: [R] swapping with data.frame

Hi! True. Randy Zelick wrote me today that it is not working. I asked him to send his observation to the list. I bymyself was trying today to find a solution but its a subotimal one in comparsion with yours. Sorry for the wrong solution and Thanks. Eryk *** REPLY SEPARATOR

RE: [R] How do i draw a step function using R?

I believe the posting guide suggests that you not ask the question in the subject... plot(..., type=s) or ?stepfun Andy From: john miller __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help PLEASE do read the

Re: [R] Distributed computing with R

If you do some programming, you might want to look at MPI. R-extensions for MPI exist (RMPI). It all depends a lot on what kind of usage you envisage of your cluster. Open-PBS is also a good batch system. Maybe you also want to look at Mosix, which is a modified linux system. Depending on what

Re: [R] Distributed computing with R

Also see SNOW (which simplifies parallel programming, sits on top of rpvm, Rmpi, or a socket-based system). Depends on whether you want parallelism on the: 1. User-level -- the libraries such as PVM, LAM-MPI, etc will help, and there are various packages which provide an API

[R] Missing data diagnostics and apology

Greetings again, Seems I've touched a nerve with my previous post and after a few kind folks alerted me to a better distribution method I chose to put the code here: http://egad.psych.arizona.edu/mddiag.final.R.gz Any tips, criticisms, or additions are welcomed. Thanks for your patience. --

Re: [R] zipping a new package

On Sun, May 30, 2004 at 03:19:24PM -0500, Laura Holt wrote: Dear R People: I have finally created a little R package. Do I need to do anything special to create a zip file for that package, or just use Winzip, please? thanks so much R Windows Version 1.9.0 Re-read Writing R

Re: [R] Using postscript() in a script that is source()ed

On Wed, 2 Jun 2004, Anthony Darrouzet-Nardi wrote: I have a script that draws 9 graphics which I would like to run by source()ing the file. In the script I make objects that contain each of the graphics (all lattice objects or functions that contain lattice functions). Then at the end of the

[R] Sloppy argument checking for named arguments

Dear R Gurus, i recently noticed that R does sloppy argument checking for named arguments, if the argument contains a dot. Example: f - function(foo.bar=0) { print(foo.bar) } f(foo=1) [1] 1 I guess, this should be considered as a bug. Anyway, the consequence is that bugs caused by typing errors

Re: [R] Distributed computing with R

I would suggest installing PVM or LAM-MPI and using the R packages `snow' and `rpvm' (or `Rmpi'). I've found the `snow' package very simple to use and useful for quick and dirty solutions. I've used `snow' with an openMosix setup and on a simple cluster of workstations without any scheduler.

RE: [R] Sloppy argument checking for named arguments

Christian -- This is not a bug, but a feature, and the dot is not the issue here. R uses partial argument matching on function arguments. So: f - function(foobar = 0){print(foobar)} f function(foobar = 0){print(foobar)} f(fo=1) [1] 1 f(foo=1) [1] 1 f(foob=1) [1] 1 f(fooba=1) [1] 1

[R] returning strings to R from C functions

I'm using .C() and .External() and have no problems sending integers, reals or strings from R to C. Nor do I have problems sending integers or reals back from C to R. But I'm pulling my hair out trying to set a string value in a C function and then sending it back from C to to R. I've searched

Re: [R] Sloppy argument checking for named arguments

It has already been pointed out that partial matching is a feature. However, if the function uses ... then it will only match arguments exactly so if you want to write a function in which full matching only is accepted you can do it by putting in a dummy first argument of ... and then issuing