similar to: branch cuts of log() and sqrt()

Hi all, I'm a PhD student at sydney uni and am trying to run a non linear mixed model program to obtain estimates of parameters describing dairy cow lactation curves. At present, I have been able to get the data to converge using the S plus (S plus 2000) nlme function. However, when I put the same data into R (R 1.9.0), add in the nlme package and run the code, it does not converge by the

Hi I'm sorry about the triviality of my problem. I have a vector (v) of three columns (logA, logB, id). I want to compute (and plot) the correlation between logA and logB for different thresholds of id (e.g. >30, etc). So I tried: for(i in 1:100){ points(cor(v$logA[v$id>i], v$logB[v$id>i], use="complete.obs"), i)) } (i created a plot object already) but it comes with

Dear all, Suppose I have a linear mixed-effects model (from the package nlme) with nested random effects (see below); how would I present the results from the random effects part in a publication? Specifically, I?d like to know: (1) What is the total variance of the random effects at each level? (2) How can I test the significance of the variance components? (3) Is there something like an

Dear all, Suppose I have a linear mixed-effects model (from the package nlme) with nested random effects (see below); how would I present the results from the random effects part in a publication? Specifically, I?d like to know: (1) What is the total variance of the random effects at each level? (2) How can I test the significance of the variance components? (3) Is there something like an

Is there an R-language interface to the R API C-language functions Rf_logspace_add() and Rf_logspace_sub()? I don't see one but I may not looking under the right name. Various packages have functions which do that same sort of thing (log(exp(x)+exp(y)) and log(exp(x)-exp(y)) without unnecessary floating point errors). They have names like matrixStats::logSumExp(lx, na.rm=FALSE, ...)

Dear R Help, I work with the Sage project, and we are trying to improve the ability to use R through Sage. Most things work, but make check seems to cause problems on certain platforms, and now that we want to upgrade to 2.10.1 I thought we should ask for help! R builds just fine on both Mac and Linux, but some things in make check seem to break on certain Linux boxes that don't on Mac or

Dear R users, according the help(log), the function log2(x) should give the natural logarithm of x. I expect in case of x=2 to to get 0.6931, however, R gives me 1 as a result. Similar, logb(2,2) gives 1 again. I'm wondering if I have missed something ? Yours Frank -- Frank Mattes, MD e-mail: f.mattes at ucl.ac.uk Department of Virology fax 0044(0)207 8302854 Royal Free Hospital

Hi [MacOsX 10.4.6; R-2.2.1] I have a bundle that comprises three packages. I want to run R CMD check on each one individually, as it takes a long time to run on all three. I am having problems. The bundle as a whole passes R CMD check, but fails when I cd to the bundle directory and run R CMD check on a package directory. The whole bundle passes: octopus:~/scratch% R CMD check

Hello everybody. I am trying to upgrade from R-1.9.0 to R-1.9.1 on a RedHat linux 2.4.18 system. I get the following error after "tar -xvzf R-1.9.1.tgz ; cd ./R-1.9.1/ ; ./configure" and "make" : [make works for 10 minutes ... snip ...] varExp text html latex varFixed text html latex varFunc

Hi the following gave me a shock: > atan(2) [1] 1.107149 > atan(2+0i) [1] -0.4636476+0i > or, perhaps more of a gotcha: > atan(1.0001+0i) [1] -0.7853482+0i > atan(0.9999+0i) [1] 0.7853482+0i > evidently atan()'s branch cuts aren't where I thought they were. Where do I look for documentation on this? -- Robin Hankin Uncertainty Analyst National

Survfit had a bug in some prior releases due to the use of both unique(times) and table(times); I fixed it by rounding to 15 digits per the manual page for as.character. Yes, I should ferret out all the usages instead, but this was fast and it cured the user's problem. The bug is back! A data set from a local colleage triggers it. I can send the rda file to anyone who wishes. The

Dear All, According to the Sturges rule, the number of classes of a histogram is the closest integer to 1 + logb(n,base=2) where n is the number of observations. The function hist(), by default, uses the Sturges rule. However, the code x <- 1:200 hist(x) produces a histogram with 10 classes and not 9 classes as determined by the Sturges rule. What am I missing? Thanks in advance, Paul

[ Not sure why, but the first time I sent this it never seemed to go through; apologies if you're seeing this twice ... ] I have some fully functional code that I'm guessing can be done better/quicker with some savvy R vector tricks; any help to make this run a bit faster would be greatly appreciated; I'm particularly stuck on how to calculate using "row-wise" vectors

What is wrong in the following nested if-else statements: if (Condition_1) { # begin IF_1 statement_1 statement_2 statement_3 if (Condition_2) { # begin IF_2 a<- a +1 } # end IF_2 statement_4 statement_5 statement_6 statement_7 if (Condition_3) {

Dear R-users, I am using R 2.13.0 and rms 3.3-0 , but can not reproduce figure 7.8 of the handouts *Regression Modeling Strategies* ( http://biostat.mc.vanderbilt.edu/wiki/pub/Main/RmS/course2.pdf) by the following code. Could any one help me figure out how to solve this? setwd('C:/Rharrell') require(rms) load('data/counties.sav') older <- counties$age6574 + counties$age75

I have a MLE task that for a small number of parameters finishes in a reasonable amount of time, but for my "real" case (with 17 parameters to be estimated) either takes far too long (over a day), or fails with "computationally singular" errors. So a) are there any parallel implementations of optim() (in R or otherwise) and b) how can I make my function more robust?

Hello everyone I am finding complex numbers to be printed oddly in R-alpha. > 1e100+1e100i [1] 1e+100+1e+100i > 1e100 + 1e44i [1] 1e+100+100000000000000008821361405306422640701865984i > dput(1e100+1e44i) 1e+100+100000000000000008821361405306422640701865984i > [same thing at home on a linux box] The first line is what I would expect, the second and third lines aren't: I

Hi try this: p3dpairs <- function(x,x1, xlim=NULL,ylim=NULL,zlim=NULL,col=par("col"), pch=par("pch"), cex=par("cex"), ...){ if(is.matrix(x)){ z <- x[,3] y <- x[,2] x <- x[,1] } if(is.matrix(x1)){ z1 <- x1[,3] y1 <- x1[,2] x1 <- x1[,1] } if(missing(zlim)) { z.grid <-

Hi I recently uploaded package "elliptic" to CRAN. From the DESCRIPTION file, it is: A suite of elliptic and related functions including Weierstrass and Jacobi forms. Also includes various tools for manipulating and visualizing complex functions. enjoy rksh -- Robin Hankin Uncertainty Analyst National Oceanography Centre,

Dear List I have just uploaded a new package, "onion", to CRAN. It provides some functionality for manipulating and visualizing quaternions and octonions. All comments welcome! enjoy rksh -- Robin Hankin Uncertainty Analyst National Oceanography Centre, Southampton European Way, Southampton SO14 3ZH, UK tel 023-8059-7743 _______________________________________________