similar to: R-alpha: R 0.50.a1 problems with lm/glm methods

Problems in R but not in S: --------------------------- 1) 'unlist' seems to have several other problems than the ones reported up to now. For instance, 'unlist' can be used on almost any object in S without much trouble. Eg.: S> unlist(c(2)) [1] 2 S> --- R> unlist(c(2)) Segmentation fault (core dumped) This occurs in R-0.49 and in R-0.50-a1. 2) Problem with the

In CHANGES, it says ------------------------------------------------------------ >> BUG FIXES ........ >> o Comments are handled better in functions. The rule is that they >> are shifted to just before their statements. Comments after the >> last statement of a function are lost. ------------------------------------------------------------ I think we could

In summary.glm I'm trying to get a better feel for the z output. The following lines can be found in the function 1 if (p > 0) { 2 p1 <- 1:p 3 Qr <- object$qr 4 coef.p <- object$coefficients[Qr$pivot[p1]] 5 covmat.unscaled <- chol2inv(Qr$qr[p1, p1, drop = FALSE]) 6 dimnames(covmat.unscaled) <- list(names(coef.p), names(coef.p))

The current version of S_alloc in src/main/memory.c is char *S_alloc(long nelem, int eltsize) { unsigned int i, size; char *p = R_alloc(nelem, eltsize); for(i=0 ; i<size; i++) p[i] = 0; return p; } which segfaults because `size' is not initialized. I am not what the right fix is, adding size = nelem * eltsize; before the loop seems to work. As an aside ... I think the seed*

Two things. TASKS has TASK: Naming with Numeric Values and "unlist" STATUS: Open FROM: <hornik@ci.tuwien.ac.at> R> l <- list("11" = 1:5) R> l $11 [1] 1 2 3 4 5 R> unlist(l) 111 112 113 114 115 1 2 3 4 5 [ Bug or feature ? ] This seems to be a feature (at least, SPLUS does the same), so please close that task. *** However, please add

Here's something really strange. ******************************************************** R> x <- 1:5 R> x [1] 1 2 3 4 5 R> test1 function (x) { structure(x, call = sys.call()) } R> test1(x) [1] 1 2 3 4 5 attr(,"call") test1(x) R> test2 function (x) { attr(x, "call") <- sys.call() x } R> test2(x) Error: stack overflow

Applying the following patches closes the following task (part 1 was already taken care of). TASK: New Problems STATUS: Open FROM: <Kurt.Hornik@ci.tuwien.ac.at> New minor remarks: * The documentation for `image' still has the old order z, x, y. * Perhaps one should add `par(ask = T)' in the image demo? * Perhaps one should save the original value

Here are some misc comments on graphics. * I am not sure whether `adj' works correctly. When using e.g. title(sub = "SUBTITLE", adj = 0) shouldn't the subtitle appear on the very left? It seems that justification is done off the middle of the plot window. * S barplot has argument `horiz', R does not. * More importantly, the barplot() argument `space' is treated

The patch below fixes the NChisquare documentation problem that I've been mentioning for some time now. NOTE: There is one DEQN where the LaTeX part contains real LaTeX code, because I did not see how to get a sum sign (and a roman math font) otherwise. Seems to work, though ... MARTIN? -k ********************************************************************** ***

A second patch for R-0.50-a1 is available from ftp://stat.auckland.ac.nz/pub/R The patch produces the following changes o cpoly problem with pow_di fixed. o legend had a call to "text" with an incorrect argument tag. Changed "text" to "labels". o The variable "dup" was uninitialised in the function "naoktrim" in

A set of patches for R-0.50-a1 is now available as ftp://stat.auckland.ac.nz/pub/R/R-0.50-a1.patch1.gz The patches mainly fix problems reported since R-0.50-a1 but some older problems are also fixed. Here is the list of changes. Ross o Many subsetting and mutation problems with the new "expression" type have now been fixed. o When ask=T is set in par() the user is instructed

Thanks for the discussion. I do feel quite strongly that the variables should always be a part of a data frame. Then functions such as summary() and pairs() can operate on them all simultaneously.... regression is only one part of the analysis. And what if there are lots of variables? Have them all scattered about the workspace? One of them could be easily overwritten. The generic predict() will

Perhaps I'd better not send any bug reports in order not to delay the release of 0.50 ... but nevertheless. R> x <- rnorm(20) R> y <- rnorm(20) R> z <- lm(y ~ x) R> typeof(z) [1] "list" R> unlist(z) [[1]] [1] 0.07030757 [[2]] [1] -0.1790483 [[3]] NULL [[4]] NULL and many more ending in [[152]] NULL [[153]] NULL [[154]] NULL Hmm ...

Hello, I am using R to train a logistic regression model and save the resulting model to disk. I am then subsequently reloading these saved objects, and using predict.glm on them in order to make predictions about single-row data frames that are generated in real-time from requests arriving at an HTTP server. The following code demonstrates the sort of R calls that I have in mind: > cases

I imitated predict.glm, my thing worked, now I need to revise. It would help me very much if someone would explain predict.glm line 28, which says object$na.action <- NULL # kill this for predict.lm calls I want to know 1) why does it set the object$na.action to NULL 2) what does the comment after mean? Maybe I need a pass by value lesson too, because I can't see how changing that

Full_Name: Marek Ancukiewicz Version: 2.01 OS: Linux Submission from: (NULL) (132.183.12.87) It seems that the the standard error of prediction of the linear regression, caclulated with predict.lm is incorrect. Consider the following example where the standard error is first calculated with predict.lm, then using delta method. and finally, using the formula rms*sqrt(1+1/n+(xp-x0)^2/Sxx). Marek

I have completed a binomial GLM in R (details attached (finalModel.docx)) and I am trying to create a graph of observed and fitted values using the following commands: > MyData<-data.frame(time=seq(from=0,to=1323,by=1)) > Pred<-predict(M2,newdata=MyData,type="response") > plot(x=turtle$time,y=turtle$success) > lines(MyData$time,Pred) However, I get the following

[Copied to R-devel for information] This applies to all versions of R I have: 0.62.2, 0.62.3, 0.63. Great care seems needed with glms with offsets, as many things seem wrong. Consider the following: > data(freeny) > freeny.glm <- glm(y ~ offset(lag.quarterly.revenue) + price.index + income.level + market.potential, data=freeny, subset=1:30) > predict(freeny.glm) Qtr1

Hi all I have run into a case where I don't understand why predict.lrm and predict.glm don't yield the same results. My data look like this: set.seed(1) library(Design); ilogit <- function(x) { 1/(1+exp(-x)) } ORDER <- factor(sample(c("mc-sc", "sc-mc"), 403, TRUE)) CONJ <- factor(sample(c("als", "bevor", "nachdem",

Problems with predict and lines in plotting binomial glm Dear R-helpers I have found quite a lot of tips on how to work with glm through this mailing list, but still have a problem that I can't solve. I have got a data set of which the x-variable is count data and the y-variable is proportional data, and I want to know what the relationship between the variables are. The data was