Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down on April 23, and its replacement, statalist.org is already up and running.


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

st: Problems with gllamm command


From   Joseph Padgett <josephpadgett@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   st: Problems with gllamm command
Date   Thu, 7 Jun 2012 10:56:42 -0400

I am using gllamm to run 3-level logistic and ordered logistic models
analyzing a college student sexual behaviors.

I am having trouble calculating predicted probabilities after saving
results from the regression models.

my model - - - - -

use database
keep if harmonized==1

gllamm DV(binary) IV-1 IV-2 IV-3 ... IV50, family(binomial) link(ologit) ///
                            i(respondent school) nip(20) eform adapt from(a)

estimates save model_1

- - - - - -

I set the above model to run on a high powered computing cluster.
After the model is complete I download the saved estimates to my
workstation.
I then issue the following commands on my local workstation - - - -


use database
keep if harmonized==1

estimates use model_1

gllamm, eform

estimates store model_1

gllapred prob, mu marginal

- - - - - -

At which point I receive the message - - - -

insufficient observations
r(2001)

- - - - - -

I have 22,674 cases, so it seems like I should have sufficient
observations for the calculation to work.

Any one have any suggestions as to what my problem is here?

Thanks!
*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/


© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index