In following the recent threads, it appears the MI functionality is an area
of active development in Zelig.
Currently, I'm trying to figure out is how to extract a *combined*
variance-covariance matrix from an analysis using MI datasets, for
post-estimation purposes. Is this possible? The generic extractor vcov()
doesn't seem to work in this particular case.
Appreciate any suggestions,
- David
David Huh, PhD
Postdoctoral Fellow
Center for the Study of Health and Risk Behaviors (CSHRB)
Psychiatry and Behavioral Sciences | University of Washington
1100 NE 45th Street, Suite 300
Seattle, WA 98105
website: <http://staff.washington.edu/dhuh>
http://staff.washington.edu/dhuh
<mailto:dhuh@uw.edu> dhuh(a)uw.edu | tel: 206.616.1997 | cell: 206.552.9848 |
fax: 206.616.1705