similar to: "predict" function does not provide SE estimates for multivariate timeseries VAR models?

Hi I want to write a little function that takes a matrix X of size m-by-n, and a list L of length "m", whose elements are matrices all of which have the same number of columns but possibly a different number of rows. I then want to get a sort of dumbed-down kronecker product in which X[i,j] is replaced by X[i,j]*L[[j]] where L[[j]] is the j-th of the "m" matrices. For

I have found a strange scoping problem in Sweave. The following Rnw file doesn't produce the same output in Sweave as it does if I produce an R file using Stangle and execute that: \documentclass[12pt]{article} \begin{document} <<R>>= election <- data.frame(A=1:3, B=9:7, C=rep(0,3)) partytotal <- rep(0, ncol(election)) for (i in 1:ncol(election)) { partytotal[i] <-

Hi look at the following session, in which I have a dataframe, and I want to extract the second row, without the first column. Everything works as expected until the last line, where I set the names of x to NULL, and get a non-desired object (I want c(4,3).). Three questions: (1) why is as.vector(a[2,-1]) not a vector? (2) How come setting names to NULL gives me bad weirdness? (3) Can I

I need to make a bunch of PDF files of histograms. I tried gatelist = unique(mdf$ArrivalGate) for( gate in gatelist) { outfile = paste("../", airport, "/", airport, "taxiHistogram", gate, ".pdf", sep="") pdf(file = outfile, width = 10, height=8, par(lwd=1)) title=paste("Taxi time for Arrival Gate", gate, "by

Hi, I've been trying to get this working for ages, but it causes R to hang. Here is my C code saved as test1.c # include <R.h> # include <Rmath.h> void test1 (double *x, double *result) { result[0] = rgamma(*x, 2.0); } This was compiled using R CMD SHLIB test1.c & loaded in R using: dyn.load("test1.dll") out <-

Hello! I am writing some functions and I repeatedly acces internal factor codes. I figured out that internal codes are 1:n where 1 represents 1st level, 2 2nd level etc. This is not documented and I wonder if this is on purpose and subject to change or would be a good idea to add this to documentation for factor? I can prepair a pacth if this is accepted. -- Lep pozdrav / With regards,

When a graph is saved as PostScript, the bounding box is often too big. A consequence is that when the graph is included in a LaTeX document, the spacing does not look good. Is this a recognized problem? Is someone working on it? Could I help? David

Full_Name: Myung Geun Kim Version: 2.4.0 OS: Window XP Submission from: (NULL) (210.110.8.105) For the data c1 of size 14, stem provides the following result. ************************************************************** >c1 [1] 14 39 70 11 38 20 37 15 41 74 74 34 48 51 ZZangi>stem(c1) The decimal point is 1 digit(s) to the right of the | 0 | 145 2 | 04789 4 | 181 6 | 044

I want to do the following: DEVw=500 DEVh=350 fname="my_plot" dev.print(file=fname, device=FOO, width=DEVw, height=DEVh, bg="transparent") How do I do this such that I can specify FOO to be one of several choices? (GDD, PNG, postscript, etc.) If I make FOO a character variable, then "dev.print" complains. I tried a simpled "substitute" but

Dear R community, I'm fitting a complex mixed-effects model that requires numerous iterations and function evaluations. I note that nlminb accepts a list of control parameters, including eval.max. Is there a way to change the default eval.max value for nlminb when it is being called from lme? Thanks for any thoughts, Andrew -- Andrew Robinson Department of Mathematics and Statistics

## While in R v. 2.3.1 (the mid-July patch for Windows) ## on a Windows XP machine, this call to order() works fine... order(1:10,decreasing = TRUE) ## [1] 10 9 8 7 6 5 4 3 2 1 ## ...however, the argument name 'decreasing' ## must be typed in toto (note the missing 'g' ## in the following): > order(1:10,decreasin = TRUE) ## Error in order(na.last, decreasing, ...) :

I want to know how to get trace of product of matrices **faster** when the matrices are really big. Unfortunately the matrices are not symmetric. If anybody know how to get the trace of it, please help me. An example is as below. n <- 2500 a <- matrix(rnorm(n*n),n,n) b <- matrix(rnorm(n*n),n,n) tr1 <- sum(diag(a %*% b)) tr2 <- sum(diag(a %*% b %*% a %*% b)) Thanks, Yongwan Chun

Dear all, seems that easy question but cannot find the function for that. How to get the elements of the minor diagonal of the matrix? Thanks a lot. [[alternative HTML version deleted]]

OK, my last question didn't get any replies so I am going to try and ask a different way. When I generate contrasts with contr.sum() for a 3 level categorical variable I get the 2 orthogonal contrasts: > contr.sum( c(1,2,3) ) [,1] [,2] 1 1 0 2 0 1 3 -1 -1 This provides the contrasts <1-3> and <2-3> as expected. But I also want it to create <1-2> (i.e.

Question: I installed R verison 2-12.0 on my Windows 7 (64 bit) PC. When I was installing it, it did not ask me anything about 32 vs. 64 bit. So, if I run R now - is it running as a 32-bit or a 64-bit? thank you! -- Dimitri Liakhovitski Ninah Consulting www.ninah.com

Hi, Given some example data: dat <- seq(4, 7, by = 0.05) x <- sample(dat, 30) y <- sample(dat, 30) error <- x - y I have broken the rage of x into 10 groups and I can calculate the bias (mean(error)) for each of these 10 groups: groups <- cut(x, breaks = 10) max.bias <- aggregate(error, list(group = groups), mean) max.bias group x 1 (4,4.3] -0.7750000 2

This is a very simple question but I couldn't form a site search quesry that would return a reasonable result set. Say I have a vector: x <- c(0,2,3,4,5,-1,-2) I want to replace all of the values in 'x' with the log of x. Naturally this runs into problems since some of the values are negative or zero. So how can I replace all of the positive elements of x with the log(x) and the

Dear All, Is this right? > floor((5.05-floor(5))*100) [1] 4 I would expect 5, or am I wrong? Thanks and regards, W --------------------------------- [[alternative HTML version deleted]]

Hi everyone, I am trying to use the function as.date() from the "dates" package in R 2.10.0 to convert a character date to a Julian date, as follows: > as.date("02-MAY-01", order="mdy") # convert May 2, 2001 to a Julian date [1] 2May1 However, when trying to convert a character date from the year 2000 to a Julian date, I get an <NA> instead of the desired

Hello, I have a list (mode and class are list) in R that is many elements long and of the form: >length(list) [1] 5778 >list[1:4] $ID1 [1] "num1" $ID2 [1] "num2" "num3" $ID3 [1] "num4" $ID4 [1] NA I'd like to convert the $ID2 value to be in one element rather than in two.?? It shows up as c(\"num2\", \"num3\") if I try to use