 |
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]
Re: st: -est combine-?
On Jul 31, 2007, at 12:26 PM, Ben Jann wrote:
Michael, I think the approach using -erepost- works best in your case.
Here is an example.
Thanks, Ben. By yesterday morning I had worked out some code that
more or less delivered what I was looking for, but yours is much
cleaner and more robust. A few brief comments are below.
Step 1: estimate the nl model and make a hardcopy of the AIC/BIC
measures (adding the nlcom results later on screws up computation of
the information measures)
Wow, thanks -- I might have missed that had you not pointed it out.
Step 2: Get a hold of the coefficients and variances. (Note that the
covariances are dropped here to keep things easier. The covariances
are not needed for tabulation.)
Step 3: run nlcom and add the results to b and V; then post
everything in e()
The use of just the diagonals of the VCE is also quite inspired; I
had spent some time trying to get that matrix correct (including row
and column equation and variable labels), but your code is much more
efficient.
Step 4: apply esttab
Adding a line between the nlreg and nlcom results is a bit tricky. The
following command would do:
/*----------------------------------------------*/
. esttab NLreg NLregNLcom, p nostar ar2 scalars(AIC BIC) nodepvar
eqlabels(,none) ///
> varl(,blist(d1 "{hline @width}") begin("" "") nofirst)
Ah, you read my mind! Not only would I likely not have figured this
out on my own, but I probably would have sent a message today with
exactly this request. One follow-up question: in experimenting to
understand the syntax, it doesn't appear that excluding the "nofirst"
suboption has any impact on the final table (at least in SMCL
format). What role is it playing?
Thanks again; I'm off to collect some results and then modify the
code to produce booktabs LaTeX output. -estout- is truly a powerful
package, and I appreciate your assistance in helping to utilize its
power.
-- Mike
*
* 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/