[R] More on problem with polr

[Anon.]

(those concerned about finding out who I am will find clues carefully
hidden towards the end of this message)



Briefly, I'm using polr (from the MASS library) to re-run an analysis I
did about 18 months ago, with a previous version of R (I'm now using
1.5.0, I think I was using 1.2.x or 1.1.x before).  It ran fine before,
but now I'm getting an error.  David Duffy suggested I post a minimum
data set to demonstrate the problem, so here is one which shows the
error - not having the old versoin of R, I can't check whether it would
work with that:

> Habitat <- factor(c(1, 1, 1, 1, 1, 2, 1, 1, 2, 1, 1, 1, 1, 1, 1, 1, 1, 1))
> Wings <- factor(c(3, 2, 2, 3, 2, 2, 2, 3, 2, 2, 3, 3, 3, 3, 3, 2, 3, 2))
> Ext <- factor(c(1, 1, 2, 5, 2, 2, 2, 2, 2, 1, 7, 7, 1, 2, 3, 1, 4, 2), ordered=TRUE)
> 
> library(MASS)
> 
> Model1 <- polr(Ext ~ Habitat + Wings)
> Model2 <- polr(Ext ~ Habitat * Wings)
Error in optim(start, fmin, gmin, method = "BFGS", hessian = Hess) : 
        non-finite value supplied by optim
> 

The full data set is much bigger (over 380 observations), but I can
provide it if someone wants to look at it in more detail.  The full data
set does have "holes" in it (i.e. combinations of levels with no
observations), but similar data sets with the same sorts of holes run
fine.

Thanks in advance for any help!

Bob

-- 
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
Finland

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
meaning
- 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
_._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._