Statalist


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

st: Constructing the variance-covariance matrix, Sigma, after -xtmixed-


From   "Joseph Coveney" <jcoveney@bigplanet.com>
To   <statalist@hsphsun2.harvard.edu>
Subject   st: Constructing the variance-covariance matrix, Sigma, after -xtmixed-
Date   Sun, 18 Oct 2009 14:13:51 +0900

With the linear model defined as 

Y ~ N(Xbeta, Sigma)

with Sigma defined as the (block-diagonal) n × n variance-covariance matrix for
random effects as well as residual error, what is the best way to reconstruct
Sigma from the parameter estimates returned by -xtmixed-, i.e., e(b), and the
information in the random-effects portion of the command line (the stuff after
"||")?

The intended use of Sigma is for small to at most moderately sized datasets.

Joseph Coveney




*
*   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   |   What's new   |   Site index