search for: masha

I have used Splus 3.4 for UNIX and I have a C file that I compiled using "Splus COMPILE" and later called with dyn.load() and .C(). It works in Splus. I want to do the same thing in R, as in just use my .s and .c files and find the equivalent of "Splus COMPILE". I've ran into lots of problems trying to do this in Windows so far, so please help! My questions are: - Do

...t; #include <sys/types.h> #include <stdlib.h> and I have the recommended MinGW compiler. Any suggestions? 2. I get a warning about having CRLF line endings in the C code, but I saved the .c files as ASCII in Notepad. Is this really a problem? How can I get rid of these? Thank you, Masha

Hello, I've encountered the following: > n_500 > tau_.95 > (n*(1-tau)) [1] 25 > (n*(1-tau))<=25 [1] FALSE > (n*(1-tau))==25 [1] FALSE I'm using UNIX R Version 1.4.0, and also tested in out in Windows 1.6.0. Is this a bug? Masha

Hello, Is there a function/package that can do multinomial logistic regression using survey weights, similar to "svymlogit" in Stata? It appears that only "svyglm" function (which does not allow multinomial response?) is available in the "survey" package. Thank you! Masha Kocherginsky