they can, but we focus on quantities of interest. so clarify combines the
simlations from each of the separate runs. from that you can calculate
any quantity of interest, as well as uncertainty measures such as
confidence intervals or t-tests, etc.
Gary
On Wed, 4 Jan 2006, Mathieu Turgeon wrote:
> Dear Dr. King,
>
> I hope this email finds you well. I am using Clarify with the mi function
> (the missing values being imputed using Amelia), and when the output
> returns, it has no statistics provided like R-squared and F-test, only the
> number of observations. Can't these statistics be computed? Please find
> attached the Stata output.
>
>
>
> Thank you,
>
> Mathieu
>
>
>
>
--
Clarify mailing list served by Harvard-MIT Data Center
[Un]Subscribe/View Archive: http://lists.hmdc.harvard.edu/?info=clarify