[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]
RE: st: Predictions based on reoprob and gllamm
Thanks for the explanation!
Now my problem is that whatever I try with gllapred I get "insufficient
observations" in return. I have 2237 observations of 153 countries from the
years 1976-1995 (unbalanced dataset).
Given that I have too few observations for gllapred, how can I then present
my results so that the substantial impact of the most interesting
independent variables can be appreciated?
Thanks for your attention.
> -----Original Message-----
> From: firstname.lastname@example.org
> [mailto:email@example.com]On Behalf Of Sophia
> Sent: Friday, February 27, 2004 9:44 PM
> To: firstname.lastname@example.org
> Subject: Re: st: Predictions based on reoprob and gllamm
> The thresholds are applied to the latent response y*
> underlying the observed response y.
> y* can take on any value from - infinity to + infinity.
> If the lowest observed response category, say 1, happens
> very rarely, the lowest threshold may have to be a large
> negative number because Pr(y=1) = Pr(y*<threshold)
> and similarly for the largest category.
> I am not sure what predictions you have considered.
> If you are referring to 'xb' (the linear predictor),
> then this is the mean of the latent response y* which
> doesn't need to lie on the range of y.
> In gllamm, you can obtain the predicted (population
> averaged) cumulative probabilities, e.g., Pr(Y>1) using
> gllapred probgr1, mu above(1) marg
> and similarly for the other categories.
> You can also get predicted probabilities for particular
> values of the random effects or posterior mean probabilities.
* For searches and help try: