hello everybody
I'm a newbie with ordered probit and with polr too.
The problem is that I have a dependent variable I need to explain
with an ordered probit that is
> head(dfscale$sod.sit.ec.fam,100)
> [1] 5 7 5 6 5 5 6 8 6 8 8 8 6 6 6 5 0 5 NA 6
> [21] 7 NA NA 0 0 2 5 3 6 6 7 6 NA 8 6 6 7 NA NA NA
> [41] 4 5 NA 10 3 9 10 10 7 5 5 5 NA NA 5 7 1 1 7 3
> [61] 6 7 NA 4 6 NA 3 4 5 3 4 4 4 5 NA 2 4 4 8 5
> [81] 5 4 6 6 5 6 7 7 7 7 7 6 8 7 6 5 5 5 6 7
so when I estimate the model
> base.op <- polr(
> as.ordered(sod.sit.ec.fam) ~
> log(y) +
> log(ncomp) +
> eta +
> I(eta^2) +
> uomo +
> elem +
> laurea +
> saluteno +
> extra
> ,
> weights = dfscale$w,
> data = dfscale,
> method = "probit"
> )
I get
> Warning in eval(expr, envir, enclos) :
> non-integer #successes in a binomial glm
Then when I try to summarize the model, in order to use xtable
> summary(base.op)
> Re-fitting to get Hessian
> Errore in optim(start, fmin, gmin, method = "BFGS", hessian >
Hess, ...) :
> valore iniziale in 'vmmin' non finito
that freely translated to english means "starting value in
'vmmin' not finished (or finite, more likely)"
what does this mean? How can I have my summary?
Thank you
Luca
--
Luca Braglia, aka Bragliozzo
http://bragliozzo.altervista.org
