similar to: Ordering in factors ...

Hi I have some data (v. large amount) with a (0,1) response where I want to minimise the errors in the betas rather than SS or deviance. So can anyone point me to a ridge regression function or equivalent for such a logistic regression case? John -.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.- r-help mailing list -- Read

Hello again Is there any way (or an alternative non-linear minimiser) that arguments to the function called in nlm can be passed in version 0.62.4? Like (I believe) nlmin in a well known other program or optimise in R. Do we use global variables? Shurely not! \John -.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.- r-help mailing list -- Read

Hello R-ists Have been lurking on the list for a while, I have noticed recently two problems: 1 There seem to be problems with installing R on SuSe Linux version 5.3. As the list only gets problems and doesn't log the successes, has anyone successfully loaded R on SuSe 5.3? Is this a feature of 0.62.3 only or do the problems apply also to earlier versions. 2 There was a list of

Hi Is there a SuSE binary package for R 0.64? John -.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.- r-help mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html Send "info", "help", or "[un]subscribe" (in the "body", not the subject !) To: r-help-request at stat.math.ethz.ch

I'm sorry if this is a basic question, but I'm stumped. I'm just trying to plot the residuals from a linear model against another variable in the data frame. Here are the lines I'm trying to execute: size <- read.table(file="/u67/abasl70/surveys/annenberg/mega/smschl.dat", header=T) sizef <- data.frame(size, row.names=size$unit) attach(sizef) mschmod <- lm

Hi all, I am having a trouble with this function I wrote ################################################### p26=function(x,alpha){ # dummy variable j=1 ci=matrix(ncol=2,nrow=3) while (j<4){ if (j==2) {x=x+c(-1,1)*0.5} ci[j,]= x+qnorm(1-alpha/2)^2/2+ c(-1,1)*qnorm(1-alpha/2)* sqrt(x+qnorm(1-alpha/2)^2/4) j=j+1 if (j==3) { # exact x=x-c(-1,1)*0.5

Having compiled and successfully installed e1071 on a previous machine (and run under 0.62.4) I want to compile it on a new machine to run under 0.63.3 but the loader can't find netpbm - both machined are RH5.2 Linux installations. I have some quite old netpbm's on a CD but none more recent and I certainly didn't install them on my old machine. I can't locate or rpm -q or rpm

Having compiled and successfully installed e1071 on a previous machine (and run under 0.62.4) I want to compile it on a new machine to run under 0.63.3 but the loader can't find netpbm - both machined are RH5.2 Linux installations. I have some quite old netpbm's on a CD but none more recent and I certainly didn't install them on my old machine. I can't locate or rpm -q or rpm

I note that the CRAN at .at land still refers to 0.63.2. Is this just a typo? I don't want to download a whole lot only to find I still have it! Does 0.63.3 live elsewhere? And I note the new function kronecker - very useful but can it be applied to non-numerics as in factors, data frames etc preserving the class, levels and names? John

I note that the CRAN at .at land still refers to 0.63.2. Is this just a typo? I don't want to download a whole lot only to find I still have it! Does 0.63.3 live elsewhere? And I note the new function kronecker - very useful but can it be applied to non-numerics as in factors, data frames etc preserving the class, levels and names? John

I have an ordering and factor problem to which there must be a simple solution! The version is R 2.0.1 (2004-11-15) on A Linux platform. A data frame H is read in from a .csv file using read.csv with as.is=TRUE. Another data frame HN is constructed from data and I want to compare two columns both named ss of the (sorted) data frames that are the same length. The problem is that HN$ss is

I have pulled Jim Lindsey's repeated library and put it under the libraries directory, as are all the other toolboxes. 2 questions: Running R COMPILE *.c and *.f goes fine except that Mathlib.h cannot be found - it is not in the include library. I cannot find any other Mathlib.h on my system anywhere - presumably this is an R specific module. Was this missing from the 0.62.4 distribution -

Despite searching (no doubt in the wrong place) I can't seem to find simple things like the linear predictor or deviance residuals from the glm() function. Obviously it is possible to code particular instances but would I be wasting my time? ie are ther such functions? \John -.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.- r-help mailing list -- Read

Hi In R 0.90.1 is there a way of stopping scan() from rewinding to the beginning of the file? Basically I have a mega-file (250Mb!!!) that I want to read and process in 301 line chunks, each line having 151 numbers on it. If I do for (i in 1:many){ pp<-scan('filename',skip=(i-1)*301,nlines=301) } it appears to do what I want but as the chunks get further down the file it gets

I want to pick out a single member for each row of a matrix according to an indexing vector and I would have thought this was a simple operation. Is it that I am too stuck in Fortran for my own good (so wots rong with fortran?), but is there a better way of doing what to me is intuitive but gives completely the wrong answer. The following result occurs: a<-kronecker(1:4,t(11:15)) # Gives

Hi I am trying to use nlm with an additional call to nlm within the function but after the first pass, the parameters to the outer call are being passed to the inner call. The inner call is a very trivial problem. ie: test.outer<-function(param.outer){ slope<-nlm(test.inner,param.inner) ... loglikelihood<-sum(...) return(-loglikelihood) } and nlm(test.outer,param.outer) on the

Hi Does anyone know of any R coding/functions for MCMC approaches? I am currently using BUGS but I wonder if the bazaar has produced anything? I think I am pushing BUGS to it's limit and possibly past it at the moment. John -.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.- r-help mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html Send

Hi Starting to use R as a serious tool, I have come across a programming problem that I can't see the answer too yet. Can someone advise me plese. The problem is that I want to plot a series of lines which represent short term growths. All the data is in a single vector and I can indicate the index via a second vector. In GLIM, if the second vector is a factor, a single $GRA Size Year

Hi I am trying to get to grips with lme and perhaps the euro-cent is not dropping. I want to define a model with some terms random and some fixed so that: gd<-groupedData(y~x|c,df) defining by the group c in data frame df, whereupon mod<-lme(y~t+f,gd,~t) where I want the t as a random effect and the f as the fixed part. Without the f it works OK but when I add the f, I get an error

This is doing my head in. Staying away from R for too long is bad for the health! I have two vectors of character names where there may be repetition and from which I want to form two factors with the same levels but only if there are more than N instances of each name in each vector. I can get the list of common names quite easily, using: