a bug and a question
Jim Lindsey <jlindsey at alpha.luc.ac.be> writes:
The question: I am getting various reports that R under MS-Windows and X-Windows/Linux on the same machine behaves very differently for nlm convergence in my libraries. Under Linux, convergence is easy with many starting values, but under MS they have to be very close to the MLE. Does anyone have experience with this and or an explanation? Is the math used different in the two systems? Jim
Not entirely unlikely. The FPU should be the same of course, but the C and math libraries link to a Microsoft DLL, which I have heard people speak badly about before. Particularly the IEEE exception handling could be causing trouble if an iterative method wanders near the boundary of a functions domain. That is pure speculation, though, I suppose Guido and Brian will know more.
O__ ---- Peter Dalgaard Blegdamsvej 3 c/ /'_ --- Dept. of Biostatistics 2200 Cph. N (*) \(*) -- University of Copenhagen Denmark Ph: (+45) 35327918 ~~~~~~~~~~ - (p.dalgaard at biostat.ku.dk) FAX: (+45) 35327907 -.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.- r-help 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-help-request at stat.math.ethz.ch _._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._