similar to: small problem with predict

Hello R helpers! I looked but did not find a table-lookup R-utility. I could use a loop to do the job (old FORTRAN/C habits die hard) but if I have a big table in which I have to search for the values corresponding to a vector, I end up logically with a double loop. Is there already such a utility? Otherwise, is there a way without loops? Thanks as always Anne

Hi all, I still have problems with the predict function by setting up the values on which I want to predict ie: original df: p1 (193 obs) variates y x1 x2 rm(list=ls()) x1<-rnorm(193) x2<-runif(193,-5,5) y<-rnorm(193)+x1+x2 p1<-as.data.frame(cbind(y,x1,x2)) p1 y x1 x2 1 -0.6056448 -0.1113607 -0.5859728 2 -4.2841793 -1.0432688 -3.3116807 ...... 192

Dear R-helpers, I have a problem which I suppose is trivila, but... I have included NA values as factors ( (to be able to make nice printed summaries with NAs % ba category ) with the following code dat$x.f<-factor(dat$x, exclude=NULL); levels(dat$x.f)<-c("A1","A2","A3","A4","NA"); length(dat$x.f) Now, I want to impute the missing values.

Sorry, sorry.... of course levels(testf)[c(2,1,3)] will do the job My excuses to all Anne PS I will meditate the following saying "la parole est d'argent et le silence est d'or" BONNES FETES A TOUS SEASONAL GREETINGS ---------------------------------------------------- Anne Piotet Tel: +41 79 359 83 32 (mobile) Email: anne.piotet@m-td.com

Hello! I would like to know if there is a simple way to reorder levels of a given factor.Let's say that the vector testf<-factor(c("red","red","red","blue","blue","white")) levels(testf) : blue red white should have reordered levels such as levels(testf) : red blue white (this is for presentation purposes) I guess

Is there an upgrate of the vcd library (visualisation of categorical data) for the latest R version? Trying to download it from CRAN I get URL /data/WWW/ftp/pub/R/bin/windows/contrib/r-release/vcd_0.1-3.4.zip was not found on this server. googling it, I found it for instance on http://www.sourcekeg.co.uk/cran/bin/windows/contrib/1.9/ but trying to install it gave me the message >

Hi! I'm trying to do some ploytomous logistic regression using multinom() in the nnet package, but am a bit confused about interpretation of the results Is it possible to get the following quantities: I: maximum likelihood estimates to test for fit of model and significance of each predictor (I would like to produce a table of the following type) Analysis of Variance: MLE (values are

Hi! Is there an easy way to add to the scree-plot labels to each value pertaining to the cumulative proportion of explained variance? Thanks and a happy new year Anne ---------------------------------------------------- Anne Piotet Tel: +41 79 359 83 32 (mobile) Email: anne.piotet@m-td.com --------------------------------------------------- M-TD Modelling and Technology Development PSE-C

Hello R helpers! I'm using the avas function form package acepack (called from areg.boot package Hmisc) to estimate automatically transformations of predictors (in this case monotonous) and response. Well, it seems to work quite well, but I have 3 basic questions: - which set of basis functions is used in this procedure? - how do I back transform my estimate (y hat ) to the originasl scale?

Hi R helpers! I'm still a bit ( alot) confused by the use of "inverseTrans" and "ytype" in areg.boot (Hmisc): What I want to do seems very simple, but I do not get the result I want: plot the predicted values in the original scale. (I did not understand the documentation, sorry!) for instance the following code

I'm about to present a report (for internal use of governmental agency). I used extensively R , contibuted packages, as well as communications on the R-list As well as citing R, I would like to know how to cite the contributed packages (it is not so easy, as some have been used exensively, other marginally, some are called from another package and some were not used as softwares but gave me

What R functionnalities are there to do missing values imputation (substantial proportion of missing data)? I would prefer to use maximum likelihood methods ; is the EM algorithm implemented? in which package? Thanks Anne ---------------------------------------------------- Anne Piotet Tel: +41 79 359 83 32 (mobile) Email: anne.piotet@m-td.com

Another newbie question.... I want to create a factor (say cT)from a numerical variable (sy temp) by regrouping the values in classes (say cT <390, [390,400[,[400,409[...>=550) Is there a simple way of doing that using the factor function? AND I do not find how to manipulate strings (I want to concatenete characters strings ("abkdas","chjw") into something like

********************************************************************** This email and any files transmitted with it are confidential and intended solely for the use of the individual or entity to whom they are addressed. If you have received this email in error please notify the system manager. ********************************************************************** Hi Just installing R and some

To the R developers, The discussion below reminded me that I think it might be a good idea to take the Relevel function from the Lexis package and replace relevel in stats with it. This is really nothing special for epidemiology. It is fully compatible with the existing relevel (it actually contains the relevel code almost verbatim as a subset), but it has the extra functionality of combining

I was wrong about needing the Relevel from the Lexis package. The default verson of relevel does the job of reshuffling levels in any desired order, albeit with a warning (which comes from the fact that apparently only a single number had been anticipated by the designer): > testf <- factor( sample( letters[1:4], 100, replace=T ) ) > table( testf, newf=relevel( testf, ref=c(3,2,1,4) )

Hi! Does somebody out there has experience with the Zelig package from Harvard uni? I have a problem when trying to set the explanatory variables with setx Polytomous logistic regression: >z.out <- zelig(OPARS ~ v1+v2+v3+...+vn, model = "mlogit", data=heb) that's OK >x.out<-set(z.out) Error in seq.Date(along = object) : `from' must be specified #??? I have no date

Hello RHelpers! I'm very ashamed but.... I'm creating quite a lot of plots in a big loop...each times the program ask me : > Hit <Return> to see next plot: How do I avoid that? Many, many thanks as always.... Anne ---------------------------------------------------- Anne Piotet Tel: +41 79 359 83 32 (mobile) Email: anne.piotet@m-td.com

Dear R helpers, this is a question connex to the subject of reading large data-sets - I have a large db (MySQL) ~80'000 records for each year / 120 variates from which I extract relevant info to be treated in R (no problem) Now each record in my db represents an experimental unit; moreover I will get - in a few days- a set of separate files(one for each records....~80'000 files pro

Hello R-helpers I want to put a color scale in a plot: I've got an xy plot where the values of the response (z=f(x,y)) is symbolically given by colors (like heat or rainbow color scale) I would like to put such a scale with apprpriates labels in the plot, so as to facilitate the interpretation (like in a finite elements result plot) How is taht possible? Thanks Anne [[alternative