Re: [R] How to stop the minimization when the condition does not hold

First you have to be more specific, what are actually the parameters of the function that you want to optiomize and what are actually constants. So you would need to specify your objective function function(theta)=lambda*(Constr)^2-f(x,theta) (which is not realy writen the R-way) as

[R] tapply and NA value

Hi, I'm writing for a little help. I have a dataframe with same NA value and I'd like to obtain the means of the value of a coloumn grouped by the levels of a factor coloumn of the datframe. I'm using the function tapply but I see that if only a NA value is present the result is NA. There is an

Re: [R] tapply and NA value

you should look at the 'na.rm=FALSE' argument of '?mean()', i.e., x - rnorm(100); x[sample(100, 10)] - NA f - sample(letters[1:5], 100, TRUE) ### tapply(x, f, mean) tapply(x, f, mean, na.rm=TRUE) I hope it helps. Best, Dimitris Dimitris Rizopoulos Ph.D. Student Biostatistical

Re: [R] tapply and NA value

I am not really sure what you mean. If I understand you correctly, than all ylu have to do is to give additiona parameter to tapply, na.rm=TRUE, tapply(, na.rm=TRUE) However as I already said, I'm not sure what you did and what is the problem. Plese provide the code that did not work,

Re: [R] learning networks with a large number of variables and pre-set parents.

This is the second time within 24 hours that you cross-posted the same question to two of the R mailing lists, please read the posting guide linked at the bottom of this mail on how to properly ask your questions. As for your question: I'm not aware of an R package that would be able to do what

[R] R: VAR package

hi all i would like to fit VAR, vector autoregressive models, to a data set. is there a package in R that does this?__ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide!

Re: [R] tapply and NA value

Thanks very much! Best of all, Leonardo Alle 10:52, venerdì 25 marzo 2005, Dimitris Rizopoulos ha scritto: you should look at the 'na.rm=FALSE' argument of '?mean()', i.e., x - rnorm(100); x[sample(100, 10)] - NA f - sample(letters[1:5], 100, TRUE) ### tapply(x, f, mean)

[R] R:var models

HI ALL i have found two package: dse and dse2. are there others__ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html

[R] newbie's question about dataframe

I have a dataframe containing X and Y. Right now, I want to create another variable in the dataframe, named Z, such that for Z = 1 for the top 10 largest value of Y and Z = 0 for the rest values of Y. I really appreciate your help. Have a great weekend.

RE: [R] newbie's question about dataframe

Something like this should do it: dat$Z - with(dat, as.numeric(Y = Y[order(Y, decreasing=TRUE)[10]])) Andy From: Wensui Liu I have a dataframe containing X and Y. Right now, I want to create another variable in the dataframe, named Z, such that for Z = 1 for the top 10 largest value of Y

Re: [R] OS X, exporting graphics, postscript()

R users, OK, so I feel dumb. I didn't understand that dev.off() turns off the process of writing a file, and that I can't open a file until dev.off() is called to complete the file. Thanks to everyone who responded to my call for help. I'm really liking what I'm learning about R. I hope to

Re: [R] newbie's question about dataframe

Liaw, Andy wrote: Something like this should do it: dat$Z - with(dat, as.numeric(Y = Y[order(Y, decreasing=TRUE)[10]])) I was just about to post dat$Z - as.numeric(rank(-dat$Y) = 10) so here it is, anyway. ;-) Uwe Andy From: Wensui Liu I have a dataframe containing X and Y. Right now, I want

Re: [R] newbie's question about dataframe

Thank you all for help. Have a nice day. On Fri, 25 Mar 2005 14:33:16 +0100, Uwe Ligges [EMAIL PROTECTED] wrote: Liaw, Andy wrote: Something like this should do it: dat$Z - with(dat, as.numeric(Y = Y[order(Y, decreasing=TRUE)[10]])) I was just about to post dat$Z -

[R] Error in save.image...recursive default argument reference

Any ideas on this one? I get the save error with compress = T also. The workspace is big. Rgui is sitting on about 300 mb of RAM. I can write objects using write.table. -Thx, Andy R save.image(lm.gs.has.run.RData) Error in save.image(lm.gs.has.run.RData) : recursive default argument

RE: [R] Tool for update

I edited Rprofile to update everything on Tuesdays. I've been doing this since 2.0 and I think I've had R running almost every Tuesday, which begs the question of what I would be doing if R hadn't come into existence. In any case, It works pretty well: ## This script gets all the packages I

[R] How to split a single vector into a multiple-column and multiple-row matrix

Dear List, I have, say, a 2000x1 numeric vector and would like to split it into, say, a 200x10 matrix. Any help is appreciated. __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide!

Re: [R] How to split a single vector into a multiple-column and multiple-row matrix

You can use 'matrix()', as in x - 1:2000 matrix(x, nrow = 200, ncol = 10) -roger R_xprt_wannabe wrote: Dear List, I have, say, a 2000x1 numeric vector and would like to split it into, say, a 200x10 matrix. Any help is appreciated. __

Re: [R] How to split a single vector into a multiple-column andmultiple-row matrix

x - rnorm(2000) dim(x) - c(200, 10) ## or if you want it by row: matrix(x, 200, 10, TRUE) Best, Dimitris Dimitris Rizopoulos Ph.D. Student Biostatistical Centre School of Public Health Catholic University of Leuven Address: Kapucijnenvoer 35, Leuven, Belgium Tel: +32/16/336899 Fax:

[R] R Reference Card (especially useful for Newbies)

Newbies (and others!) may find the R Reference Card made available by Tom Short and Rpad at http://www.rpad.org/Rpad/Rpad-refcard.pdf or through the Contributed link on CRAN (where some other reference cards are also linked) useful. It categorizes and organizes a bunch of R's basic, most used

[R] Casting in R

Hi, I am looking for functions that would allow me to access raw binary data of R vectors. One way would be to use: x = (1:10)*pi writeBin(x, temp.bin) r = readBin(temp.bin, raw, n=length(x)*8) Other to write my own C code. Is there any other simpler way? I this message

RE: [R] Casting in R

Have you looked at the XML package on CRAN? -- Bert Gunter Genentech Non-Clinical Statistics South San Francisco, CA The business of the statistician is to catalyze the scientific learning process. - George E. P. Box -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL

RE: [R] Casting in R

Yes, XML package does not seem to support Base64 encoding so I wrote my own encoder/decoder working with raw vectors. The only problem is casting R's vectors of doubles into vectors of type raw. Jarek -Original Message- From: Berton Gunter [mailto:[EMAIL PROTECTED] Sent: Friday, March

Re: [R] Bivariate lognormal distribution

Thanks to Prof. Ripley, Kjetil and Spencer Graves for help. I will be more specific. I have to simulate a bivariate lognormal pair (Y1,Y0) where E(Y1)=X'b, E(Y0)=X'd, Var(Y1)=c1, Var(Y0)=c0, X is a data matrix, and b and d are vectors of parameters. Vicky. - Original Message - From:

[R] home and search buttons in help files?

My thumb grows tired of having to back arrow so much in the help files :-( Would it be possible to add to the wish list that a link to the help index page (since the up button at the top of the package index never seems to work for me) and another link to the search page? Jeff. --- Jeff D.

[R] Gmail invitation

Hello R users! I just found out that I have 49 invitations for Gmail (gmail.google.com). I have been using it now for a while and is really nice. Don't forget 1 GB for free. I will invite those who respond to this mail by FIFO. -- Lep pozdrav / With regards, Gregor Gorjanc

RE: [R] if..else.. need help

Well, if you type that at a command prompt, the expression is complete after the end of the if so you have an else {} which is orphaned. I think people usually use this style if() { } else { } or something similar to prevent this. Reid Huntsinger -Original Message- From: [EMAIL

RE: [R] Gmail invitation

You can also buy these things on Ebay. I noticed the supply about 2 months ago when I guess you would have made about $1-2 per invitation. The profit opportunity is much diminished now that the supply has greatly increased (it appears every gmail account was allocated 50 invitations instead of 5 a

Re: [R] Gmail invitation

I got 48 if anyone wants em just let me know. :-) ~Erithid Gorjanc Gregor wrote: Hello R users! I just found out that I have 49 invitations for Gmail (gmail.google.com). I have been using it now for a while and is really nice. Don't forget 1 GB for free. I will invite those who respond to this

Fwd: Re: [R] Prediction using GAM

Note: forwarded message attached. __ ---BeginMessage--- Subject: Re: [R] Prediction using GAM To: Prof Brian Ripley [EMAIL PROTECTED] In-Reply-To: 6667 MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Length: 1068 The

[R] gam in library(gam)

I know there are two versions of gam in R. One is in library(mgcv) and one is in library(gam). The one in mgcv can automatically calculate the smoothing parameter. However, the one in gam can't although it can incorporate a larger variety of smoothers (besides spline). Can anybody educate me if

RE: [R] Gmail invitation

Bogdan, my charge is 0$. In the begining (in autumn 2004) I also got 5 invitations, but now I just realized I got another portion with 50. Now I have 46 left. -- Lep pozdrav / With regards, Gregor Gorjanc University of

RE: [R] Tool for update

You might want to look at the new tools in 2.1.0alpha for this sort of thing. In particular, packageStatus() is now built on top of the new tools that it may be cleaner to call directly. For what I understand you run this every time you use R on a Tuesday, which is not what I would want. On

RE: [R] Tool for update

For what I understand you run this every time you use R on a Tuesday, which is not what I would want. What's wrong with Tuesday? Indeed, it's not the ideal solution but has kept me up-to-date. What has amazed me is that I think I've used R every Tuesday (and other workdays) since I did that.

[R] Stratified bootstrap question

Dear experts, I am asking for help with a question regarding to stratified bootstrap. My dataset is a longitudinal dataset (3 measurements per person at year 1, 4 and 7) composed of multiple clinic centers and multiple participants within each clinic. It has missing values. I want to do a

[R] Trouble with expression() in R-win 2.0.1

Hi. The following statement works fine in R-win 1.8.0, but yields a syntax error in R-win 2.0.1 (and possibly in other versions after 1.8.0): plot(c(1,2),main=expression(a==b==c)) I note that the following workaround executes successfully in both versions of R...

[R] trouble with help.start()

R 2.0.1 running on Linux Core 3. I am having trouble running the HTML help system. When I issue the command help.start() as a normal users I receive the following meage help.start() Making links in per-session dir ... If /usr/bin/firefox is already running, it is *not* restarted, and you

Re: [R] learning networks with a large number of variables and pre-set parents.

Sorry, I didn't mean to break the posting rules. I just thought that r-help and r-sig-gr are two seperate mailing list. And the reason I posted my messages twice within 24 hours was that I forgot to add subjects to my first postings, so I'm afraid my first postings would be ignored at all.

Re: [R] learning networks with a large number of variables and pre-set parents.

Hi, you have 1 variables and how many cases? In my experience you need a lot of memory working with this kind/size of data and deal! dim(pk.df) [1] 7321 24 pk - network(pk.df) pk.prior - jointprior(pk) Error in rep.default(data, length.out = vl) : cannot allocate vector of length