Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
st: RE: -mi estimate: mean <var>-: why no SE reported?
From
<[email protected]>
To
<[email protected]>
Subject
st: RE: -mi estimate: mean <var>-: why no SE reported?
Date
Tue, 18 Mar 2014 18:18:19 +0000
Thanks, Daniel. You helpfully clarified that when there is a single observation, the (within-imputation) variance is defined as missing, rather than zero as I had assumed. In effect, I was forgetting that the sample variance involves a division by #obs minus one, not by #obs. So, there's division by zero in this single-observation case, and missing is the result.
Stephen
------------------
Stephen P. Jenkins <[email protected]>
--------------------------------------------------------------------------------