Mark asked:
> In a logistic regression model, how is it possible to let outreg
display
> the standardized factor change (which you get via "listcoef") instead
of
> the default (unstandardized) factor change? And by the way, how can I
> let it display the percentage change?
As Tim mentioned, you could use -estadd- to add the standardized factor
change coefficients and then tabulate the results using -estout-
(unfortunately, there is not -estadd- function to add percent change
coefficients; but see below). You would need to install the following
packages:
. ssc install estout
. ssc install estadd
. ssc install estadd_plus
and then type something like
. logit ....
. estadd ebsd
. estout, cells(ebsd) drop(_cons)
("ebsd" stands for exp(b*sd), i.e. the standardized factor change
coefficients)
Richard wrote:
> I'll add that Long & Freese's listcoef does not return or ereturn its
> results. Ergo, you will have to program the calculations yourself.
fitstat
> does return the estimated variance of y*, which is needed for some of
the
> standardizations done by listcoef.
Note that some time ago Scott Long and I started revising -spost-
(-listcoef-, -prchange-, -fitstat-) and writing specific -estadd-
functions in order to tabulate -spost- results in -estout-. Two thirds
of the work are done, I'd say....
Furthermore, note that I just finished revising -estadd- and writing an
easy-to-use wrapper for -estout-. The wrapper is called -esta- and
produces publication-style tables without much typing. Furthermore, I
wrote a tool called -esto- to simplify storing estimates. You may expect
the new programs sometime next week.
ben
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/