similar to: somebody's stolen my probabilities

gday R gurus, I have a multivariate regression for which I want to constrain the coefficients to be > 0. Is this possible? I've check the doco and searched CRAN but can't find anything. thanks, John Strumila -.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.- r-help mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html Send

Thanks to Brian Ripley for the time and effort put into developing the factanal package for R. I have found it very useful. However, in trying to replicate some results from previous research, I have run into the need for a couple of extensions and was wondering if they might find their way into future implementations. 1. Though maximum likelihood estimates might be more rigorous and

gday R friends, Since I had random errors with ghostscript 6.01 I thought I'd upgrade. After upgrading to gs6.5 I've had problems. Originally, gs failed complaining about lack of "__sysconf" in glibc2.2 so I upgraded glibc. Now I get this. Note that it used to work with gs6.01. I realise this is probably a ghostscript problem but you never know... thanks, John Strumila >

gday R gurus, has anyone seen this lm problem? When I add 2 bytes to the variable name (via names), lm returns an error. It's as if there's a limit to the size of the variable names. Any suggestions? thanks, John Strumila > names(y)[12:14] [1] "Log.SQLServer.Locks.RID.Lock.Wait" "Log.SQLServer.Lock" [3] "xxaa"

G'day R friends, I didn't get any replies on the main list so I thought I'd try with the experts. I was wondering if anyone's ported R to os390. If so, are the vsize and nsize limits the same as other platforms? I could really annoy those SAS guys then. thanks, John Strumila john.strumila@team.telstra.com

gday R gurus, I've never attempted to use download.file before on my win2k machine but this version 1.4 looks exciting. However, I'm not getting something right. I've passed my R shortcut --internet2 and I can tell it's using the wininet calls because it's asking about authentication but how do I tell it my username/password? The help file only talks about user/pw for non

gday R friends, I was wondering if anyone could help me with some graphics issues please. I'm processing R in batch on redhat6.2 with some graphics to be imported into msword on NT. For scaling within my doco I want some vector type graphics. win.metafile doesn't seem to be supported on redhat which gives me postscript. postscript is ideal but doesn't contain a preview so I

iterations <- 100 nvars <- 4 combined <- rbind(scaleMiceTrain, scaleMiceTest) reducedSample <- combined reducedSample <- subset(reducedSample, select = -pID50) reducedSample <- subset(reducedSample, select = -id) for (i in 1:iterations) { miceSample <- sample(combined[,-c(1,2)],nvars, replace=FALSE) miceSample$pID50 <- combined$pID50 miceTestSample <-

Could someone advise me about how to react to the message: * checking R code for possible problems ... NOTE slm: no visible binding for global variable 'response' from R CMD check SparseM with * using R version 2.6.0 Under development (unstable) (2007-09-03 r42749) The offending code looks like this: "slm" <- function (formula, data, weights, na.action, method =

howdy R friends, I've searched CRAN but to no avail... I'm trying to use mva's hclust and print out for say 10 clusters in batch. How do I do this? It's unclear if I can use cutree. thanks, John Strumila -.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.- r-help mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html Send

howdy gurus, I was wondering if someone could help me with what looks like a simple problem. I found this great function called "get" which allows me to work out my object name at run time. Unfortunately it's not letting me assign values with it. What am I doing wrong? thanks, John Strumila > names(get(file.name))[1] [1] "X14.59.23" >

I'm trying to use stepAIC on sparse matrices, and I need some help. The documentation for slm.fit suggests: slm.fit and slm.wfit call slm.fit.csr to do Cholesky decomposition and then backsolve to obtain the least squares estimated coefficients. These functions can be called directly if the user is willing to specify the design matrix in matrix.csr form. This is often advantageous in large

[This email is either empty or too large to be displayed at this time]

Hello Andy, Thank you for your offer to work together on implementing the your new scheduler on X86. I can start working on this right away. In case you were unaware, the new Silvermont micro-architecture is only out of order on the integer side. The SSE instructions are still in order, so the current postRA scheduler is very beneficial for code with lots of SSE instructions, such as the ISPC

Hi All, I created a two variable lm() model slm<-lm(y[1:3000,8]~y[1:3000,12]+y[1:3000,15]) I made two predictions predict(slm,newdata=y[201:3200,]) predict(slm,newdata=y[601:3600,]) there is no error message for either of these. the results are identical, and identical to slm$fitted as well. if this is not the right way to apply the model coefficients to a new set of inputs, what is

g'day R friends, can anyone please help me with a frustrating merge? The number of rows of a resulting merge is the smaller of the 2 dataframes used as input. What am I doing wrong? I'm using 1.1.0 on redhat 6.2 thanks, John Strumila > xx[1:10,] datetime c 948992940 948992940 0 948993000 948993000 0 948993060 948993060 0 948993120 948993120 0 948993180 948993180 0

howdy R friends, I'm new but I used to play with S+ a long time ago. Can someone please help me with how to approach this? I have some response time data I want to 'correlate' with other data. I believe queueing is involved so I need to prove somehow (F test?) that response ~ exponential(...) How do I go about this? I cant find exponential in 'nlm' or other functions.

howdy gurus, I'm new and green and I was hoping for a tiny bit of your expertise. I'm running out of virtual memory (heap?) when summing using tapply. I've already used --vsize=90M on my hpux machine. (details below) Can I pre-sort or something to prevent my error? thanks, John Strumila john.strumila at corpmail.telstra.com.au > gc()["Vcells","total"] [1]

Dear R list, members of my course have encountered the following error message: > slm <- lm(price ~ engsize, autoframe) Error in get(x, envir, mode, inherits) : variable "FUN" was not found [more context is given in the fuller listing below]. Once the error is encountered it seems to persist; for example early in one session: > summary(blin.fit) Call: lm(formula = Response

Hi, I am trying out the SparseM package and had the a question. The following piece of code works fine: ... fit = slm(model, data = trainData, weights = weight) ... But how do I use the fit object to predict the values on say a reserved testDataSet? In the regular lm function I would do something like this: predict.lm(fit,testDataSet) Thanks -Bala