[R] "New" problem with polr (again)

Anon. bob.ohara at helsinki.fi
Tue Jul 30 17:50:07 CEST 2002

I didn't get any answer to my problem last week, so I feel obliged to
ask again.

About 18 months ago I carried out an analysis of some ordinal data,
using the polr function in MASS (this would have been using either
v1.1.x or v1.2.x on Windoze).  I now have to carry out the same analysis
on the same data (but add in another factor), and I can't get it to work
(using v1.5.0).  I keep getting this message:

> ModelF <- polr(Ext ~ Habitat+Edge+Grids+SE+NH+Size+Wings+Grids:SE + Grids:NH + Habitat:Edge, na.action=na.omit) 
Error in optim(start, fmin, gmin, method = "BFGS", hessian = Hess) : 
        non-finite value supplied by optim

This is the same model as previously, and even trying several of the
much simpler models give the same result.  So, (a) what is going on, (b)
is there a "tweak" I can use to try and get it working and if so,
what?), and (c) (if all else fails) is MASS library for v1.2.x still
available (I have this at my other office, on Debian Linux)?


Bob O'Hara
Metapopulation Research Group
Division of Population Biology
Department of Ecology and Systematics
PO Box 65 (Viikinkaari 1)
FIN-00014 University of Helsinki

tel: +358 9 191 57913      mobile: +358 50 599 0540
fax: +358 9 191 57694    email: bob.ohara at helsinki.fi
<http://www.helsinki.fi/science/metapop/> is not where it's at

It is being said of a certain poet, that though he tortures the English
language, he has still never yet succeeded in forcing it to reveal his
- Beachcomber
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

More information about the R-help mailing list