similar to: Workings of model.frame.default and [.

The Design library has been fully ported to R except for Cox proportional hazards regression modeling (using Therneau's survival package) which will be available in about two weeks. It will take much longer to make all the example code executable, is it currently contains many examples for which data are not provided. Thanks to Xiao Gang Fan <xiao.gang.fan1 at libertysurf.fr> who

The Design library has been fully ported to R except for Cox proportional hazards regression modeling (using Therneau's survival package) which will be available in about two weeks. It will take much longer to make all the example code executable, is it currently contains many examples for which data are not provided. Thanks to Xiao Gang Fan <xiao.gang.fan1 at libertysurf.fr> who

In a .First.lib I want to issue two require()s to insure that two other packages are loaded. But I want the package being loaded by .First.lib using library.dynam("mypackage",pkb,lib) to be higher in the search order than the two required packages, because I want to have a couple of functions from the two required packages overridden. What is the best way to do that? Thanks in advance

I am unclear on whether to run R CMD check pgkname as user or as root on Linux. When running as user, after all the latex, html, and man files are created, I get the following error message: Rdconv(): Couldn't open '': Permission denied Has anyone dealt with that message? When I run R CMD check a second time, all latex, html, etc. are recreated which takes quite a while. Is there

I am using read.spss in the foreign package to read an SPSS save file. For date variables I get huge values such as 11489990400. Does anyone know how to convert these values to R POSIXct date objects? Thanks in advance -Frank platform i686-pc-linux-gnu arch i686 os linux-gnu system i686, linux-gnu status major 1 minor

I am trying to replicate part of the function of the S-Plus terms.inner function. I don't need an entire model terms object but R expressions or character strings containing the innermost variable name given a vector of character strings or expressions. Here are some example inputs that each should result in the string or expression "x": x; x^2; g(x); h(g(x)); h(g(x^3));

Under platform i586-pc-linux-gnu arch i586 os linux-gnu system i586, linux-gnu status major 1 minor 5.0 [1.5.1 not available for Mandrake 8.1] year 2002 month 04 day 29 language R when I modify [.factor to change the default drop=FALSE to

> From: fharrell@virginia.edu [mailto:fharrell@virginia.edu] > [snip] > I think your code is more complex that is really needed. > > The problem with defaulting to deparse(...) is that > multiple function pass-throughs return the wrong result: > [snip] > So I don't see a large role for the deparse(...) method. > Actually one of the reasons that I included the

Under platform i686-pc-linux-gnu arch i686 os linux-gnu system i686, linux-gnu status major 1 minor 5.1 year 2002 month 06 day 17 language R I am having the following problem. d <- Sys.time() w <- data.frame(d)

I am having good success in using pdf() to produce pdf graphics files for inclusion in documents processed by pdflatex [I'm using R 1.6.0 on Linux]. I am having one small problem consistently though, which I believe I also had with S-Plus's pdf.graph(): wasted space at the top of the graph which causes pdflatex to put the graph on a later page, when the current page has plenty of space.

Does anyone have something like tapply that is extremely fast for matrices when there is a very large number of levels of the grouping variable? I'm referring to, for example, tapply(x, grouping.variable, function.operating.on.submatrix) where x is a matrix and the submatrix is a subset of the rows of x. The grouping variable's length equals the number of rows of x. -- Frank E

If anyone has a very fast vectorized method for doing the following I would appreciate some help. I want to avoid outer() to limit memory problems for very large n. Let x = real vector of length n y = real vector of length n w = real vector of length m, m typically less than n/2 but can be > n z = real vector of length m For w[i], i=1,,,m, find the value of x that is closest to w[i]. In

Under platform i686-pc-linux-gnu arch i686 os linux-gnu system i686, linux-gnu status major 1 minor 6.1 year 2002 month 11 day 01 language R > x <- strptime(c('10/10/1969','12/31/2002'),format='%m/%d/%Y')

In platform i686-pc-linux-gnu arch i686 os linux-gnu system i686, linux-gnu status major 1 minor 7.1 year 2003 month 06 day 16 language R I get > sort(c(3,1,NA)) [1] 1 3 Shouldn't NAs be retained by default? Thanks -Frank ---

Full_Name: Frank Harrell Version: 1.6.1 OS: RedHat 8.0 Linux Submission from: (NULL) (128.143.108.90) I get an error when trying to load a URL that contains a file that was saved using save(object, compress=TRUE): > load('http://hesweb1.med.virginia.edu/biostat/s/data/sav/kprats.sav') Error in gzfile(file, "rb") : unable to open connection In addition: Warning message:

I frequently use hclust on a similarity matrix. In R only a distance matrix is allowed. Is there a simple reliable transformation of a similarity matrix that will result in a distance matrix making hclust work the same as S-Plus with a similarity matrix? Venables & Ripley 3rd edition implies that a simple reversal of values will suffice. Thanks -Frank -- Frank E Harrell Jr

Hi all, I'm currently working with a dataset that has quite a few missing values and after some investigation I figured that multiple imputation is probably the best solution to handle the missing data in my case. I found several references to functions in S-Plus that perform multiple imputation (NORM, CAT, MIX, PAN). Does R have corresponding functions? I searched the archives but was not

I am using GLM to calculate logit models based on cross-sectional data. I am now down to the hard work of making the results intelligible to very average readers. Is there any way to calculate a psuedo analoque to the R^2 in standard linear regression for use as a purely descriptive statistic of goodness of fit? Most of the readers of my report will be vaguely familiar and more comfortable with

Hello R-user I want to compute a multiple regression but I would to include a check for collinearity of the variables. Therefore I would like to use a ridge regression. I tried lm.ridge() but I don't know yet how to get p-values (single Pr() and p of the whole model) out of this model. Can anybody tell me how to get a similar output like the summary(lm(...)) output? Or if there is

Even though the FDA has no policies at all that limit our choices of statistical software, there is one defacto standard in place: reliance of the SAS transport file format for data submission (even though this format is deficient for this purpose, e.g., it does not even document value labels or units of measurement in a self-contained way). Because of the widespread use of SAS transport files in