Daniel, Thanks for answering.
> your AIC is monotonic increasing That was the reason I suspected something is wrong, but what? Either the way I calculate the number of estimiated parameters? Or the (scale of the) Likelihood itself? > Have you tried a dimensional reduction technique or to investigate the > wieghtings on your paramaters (eigenvalues in spectral decomp - principal components analysis). Maybe some of those factors are not contributing? The data was simulated, so we know what it is. Best regards Jens Oehlschlägel -- "Feel free" - 10 GB Mailbox, 100 FreeSMS/Monat ... ______________________________________________ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.