[R] Algorithm did not converge

Spencer Graves spencer.graves at pdf.com
Mon Apr 28 18:43:00 CEST 2003

	  "glm" tries to maximize the likelihood.  In certain cases, the 
likelihood is maximized at infinite.  This may be the case with your 
saturated model.

	  I suggest you think carefully about what you want to do, and then fit 
one or several models that avoid this problem.

hope this helps.  spencer graves

Laine, Laetitia wrote:
> Help! Being a bit of a novice, please bear with me if this is a stupid
> question!
> I am trying to fit a saturated model to some count data that I have:
> model<-glm(COUNT~SP*LOC*COL*TIME*TREAT,poisson)
> but R keeps on crashing and coming up with (occasionally before crashing) an
> error that states:
> Algorithm did not converge in: (if(is.empty.model(mt)) glm.fit.null else
> glm.fit)(x = X, y = Y,
> What am I doing wrong?
> Thanks
> Laetitia
> ______________________________________________
> R-help at stat.math.ethz.ch mailing list
> https://www.stat.math.ethz.ch/mailman/listinfo/r-help

More information about the R-help mailing list