popescul@unagi.cis.upenn.edu writes:
> Hello,
>
> I was using R for logistic regression modeling (glm() with binomial
> family) and have noticed that it' can't handle more than 100
predictors
> (reports syntax error)
> Is it a bug, or a language restiction ?
>
> I would be very grateful if you let me know possible ways around the
> problem, as I need R for problems with many attributes.
>
> Thank you,
>
> Alex.
If you get a syntax error, then I wouldn't expect that glm() itself is
causing it. More likely, you are exceeding the line length limit in
the parser. Try splitting your command over several lines, or use
simplified formulas like glm(V1~.,data=d,family=binomial).
--
O__ ---- Peter Dalgaard Blegdamsvej 3
c/ /'_ --- Dept. of Biostatistics 2200 Cph. N
(*) \(*) -- University of Copenhagen Denmark Ph: (+45) 35327918
~~~~~~~~~~ - (p.dalgaard@biostat.ku.dk) FAX: (+45) 35327907
-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-
r-devel mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html
Send "info", "help", or "[un]subscribe"
(in the "body", not the subject !) To:
r-devel-request@stat.math.ethz.ch
_._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._