yes, you can do that if you think the R^2 is really a quantity of
interest. I'm skeptical that R^2 is something you should care about but
any quantity you can calculate in one data set you can average in this way.
Gary
---
http://gking.harvard.edu
On 3/17/2009 11:02 PM, Helen Brown wrote:
Hello,
I have 10 datasets generated with mi/Amelia II. If I want to report
the R-sq, is it OK to run the regressions separately on each of the
datasets and then average the R-squared?
Thanks so much.
Helen A Brown
-
Amelia mailing list served by Harvard-MIT Data Center
[Un]Subscribe/View Archive:
http://lists.gking.harvard.edu/?info=amelia
More info about Amelia:
http://gking.harvard.edu/amelia