similar to: Aggregate drops empty subsets

< Does anyone know why they're called random deviates, as opposed to random numbers?> Others will probably give you some technical reason about random numbers can be considered as random deviates from a mean (I think at least the 1875 Galton paper at http://www.mugu.com/galton/ uses similar terminology (I'm not claiming this is the earliest use - just the easiest to access at the

Greetings all, I'm trying to figure out how to calculate the inverse CDF (i.e. a quantile) for a non-central F distribution. I could put together a quick numerical solver routine using the CDF, but I wonder if there's a function that I've missed that would be more efficient? Thank-you, Andrew Andrew Robinson Ph: 208 885 7115 Department of Forest Resources Fa: 208 885

Hello, has anyone tried to get R running on a Sharp Zaurus 5500? Andrew Andrew Robinson Phone: 208-885-7115 Department of Forest Resources Fax: 208-885-6226 University of Idaho E: andrewr at uidaho.edu Po Box 441133 WWW: http://www.uidaho.edu/~andrewr Moscow, ID 83843 and: http://www.biometrics.uidaho.edu/ No statement above

If I place par(new=T) before I create a plot in a script that is sent to a pdf device, the pdf is unopenable and reports itself as having no pages. The postscript device seems to ignore the par instruction. I guess one of these is a bug, but I don't know which one! --please do not edit the information below-- Version: platform = i386-pc-linux-gnu arch = i386 os = linux-gnu system =

Hello all, Here's my query: Running R 1.6.2 on FreeBSD 5.0, and on WinXP, and I find that the following hangs the process: dchisq(alpha=0.01, df=1, ncp=295) but it does work for ncp < 294.92. Is this general? Best wishes to all, Andrew Andrew Robinson Ph: 208 885 7115 Department of Forest Resources Fa: 208 885 6226 University of Idaho E : andrewr at uidaho.edu PO

Dear R-community, I'm using Sweave to produce reports. The reports require the "axis" command. When I run axis the program returns NULL as well as creating the axis. > plot(1:4, rnorm(4), axes=FALSE) > axis(1, 1:4, LETTERS[1:4]) NULL > So, my Sweave tex files have \begin{Schunk} \begin{Soutput} NULL \end{Soutput} \end{Schunk} in front of each graphic that requires

I don't get the same result, do you have a package loaded that would change the default behavior (such as Hmisc)? > list(grp.1) [[1]] [1] 1 2 Levels: 1 2 > list(grp.1[mask]) [[1]] [1] 1 Levels: 1 2 > library(Hmisc) <<snip>> > list(grp.1[mask]) [[1]] [1] 1 Levels: 1 --Matt > version _ platform i386-pc-mingw32 arch i386 os

Hi dear R-community, I wonder if anyone has written code that will post-process the results of a tapply to create a dataframe that includes the outcome, the factor by which the function has been applied, and, if the factor is also an interaction, then also the levels of contributing factors? >From this outcome <- tapply(data, A.B, function) I'd like to arrange something like this:

Dear R community, I'm trying to understand this behavior of TukeyHSD. My goal is to obtain defensible, labelled multiple comparisons of an interaction term. Firstly, if I plot the TukeyHSD from the model that calculates its own interactions, then the y-axis labels appear to be reflected on their median when compared to the text output of the TukeyHSD statement. The labels are integers.

Greetings R-community, I'm running simulations within R that I wrote in C. The simulations require fitting that occasionally fails to finish. I was wondering if there is any kind of tool for process control in R, such that after e.g. 15 minutes I could kill the process, record the state for post-hoc analysis, and move to the next simulation? I'm running FreeBSD and could almost surely

Greetings R community, I am curious about the following behaviour: if I define a factor, and then store a subset of it in a list, the stored version seems to drop levels that were not included in the subset. E.g. .. > mask <- c(T, F) > grp.1 <- factor(c(1,2)) > list(grp.1) [[1]] [1] 1 2 Levels: 1 2 > list(grp.1[mask]) [[1]] [1] 1 Levels: 1 It is as though the list were

Dear R community, In the excellent nlme package the default diagnostic plot graphs the innermost residuals against innermost fitted values. I recently fit a mixed-effects model in which there was a very clear positive linear trend in this plot. I inferred that this trend occurred because my fixed effect was a two-level factor, and my random effect was a 12-level factor. The negative residuals

Hi all, I'm using R 1.5.1 on Windows 2000. The following snippet of code doesn't seem to do anything - no error is reported, and there is no name change. names(myFrame[,c(1:3)]) <- c("name1", "name2", "name3") This code however works nicely: names(myFrame)[c(1:3)] <- c("name1", "name2", "name3") Can anyone suggest why

Hi all, I'm trying to find a way to get xyplot to produce a second set of axes outside the right hand side of the graph. This is my progress so far: EE <- equal.count(ethanol$E, number=9, overlap=1/4) xyplot(NOx ~ C | EE, data = ethanol, prepanel = function(x, y) prepanel.loess(x, y, span = 1), xlab = "Compression Ratio", ylab = "NOx (micrograms/J)",

Dear R friends, I know that this topic has been mulled over before, and that there is a substantial difference between the convergence criteria for JMP and those for R. I apologize that this is somwehat raking cold coals. Summary: A model/data combination achieves convergence in JMP, and survives a reasonably rigorous examination (sensible parameter estimates, well-behaved surface,

>From the viewpoint of being reliable and scaleable, I'm wondering what using realtime would really get me. Given the number of additional things that can go wrong using realtime, I'm thinking about just using the standard text config files and pushing them to the asterisk servers via scp from a configuration server. I've also thought about keeping the configs in a database but

I'd like to carry out a Monte Carlo simulation test where given data is a contingency table. I think this is something to do with using rmultinonom(), but I'm not sure how to code this, to simulate contingency tables. Could anyone please help with how to use R to simulate contingency tables like this? -- View this message in context:

Hi, I'm using R version 1.8.0 on Windows NT. When fitting a glm with Poisson random component and a log link, I frequently need to include an offset. Typically I use xtabs or table to get the counts for the contingency table, and then I use as.data.frame.table to create a data frame that I can use in the glm function. I have not found an option that allows me to total the offset variable to

Dear all, I have a dataset with qualitative variables (factors) and I want to test the null hypothesis of independance between two variables for each pair by using appropriate tests on contingency tables. I first applied chisq.test and obtained dependance in almost all cases with extremely small p-values and warning messages. > chisq.test(table(data$ins.f, data$ins.st))$p.val [1]

Hi All, I have a question regarding contingency tables. I would like to calculate the mean and standard deviation of a continuous variable from my own dataset based on the percentages of a contingency table I obtained from a scientific article. dataset<- data.frame(cbind(case=rep(0:1,5), x1=c(1:10), x2=c(0:9))) contingency_table<- matrix(c(100, 75, 65, 85, 90, 87), nrow=3, ncol=3) In