[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]
st: RE: statalist-digest V4 #2439
James wants to know about beta coefficients and outreg2.
Standardized beta coefficients can be obtained by first standardizing all
variables to a mean of 0 and a standard deviation of 1. Or you can
deflate each estiamted coefficient by its standard error after the
estimation, which is what outreg2 does. James is using analytic weights
(see http://www.stata.com/support/faqs/stat/crc36.html), which
alters that relationship. I am assuming that Stata is applying the beta
transformation prior to applying the analytic weights, but the application
of analytic weight would likely cause it to violate the beta condition of
zero means and unitary standard deviation - which is probably responsible
for the discrepancy. It would be more meaningful if the analytic weights
were first applied (by hand, if necessary) and then the beta transformation
is conducted. In that case you would have true beta coefficients.
From: James J Walters <firstname.lastname@example.org>
Subject: st: Outreg2 beta versus OLS beta
The calculation of standardized coefficients using OLS yields one set of
beta values in place of the confidence intervals. The Outreg2 command
yields somewhat different values even when derived from the stored values
of OLS with the beta option. I am using -aweights- so the -listcoef- has
not been helpful interpreting why these values are different. I will
appreciate someone pointing me in the right direction.
* For searches and help try: