[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

Re: st: -est combine-?

From   "Ben Jann" <>
Subject   Re: st: -est combine-?
Date   Mon, 30 Jul 2007 16:30:51 +0200

have a look at

Not exactly your problem, but maybe it helps. Furthermore, the
-erepost- command might be helpful (see -ssc describe erepost-). The
procedure would be to do something as follows:

ivreg2 ...
est sto base
matrix b = e(b)
matrix V = e(V)
nlcom ...
... add results to b and V
[... more nlcom commands ...]
est restore base
erepost b=b V=V
est sto modified
estout modified

If you provide more details, I can be more specific.

On 7/30/07, Michael Hanson <> wrote:
>         As part of a multi-column table of estimation results, I am looking
> to "combine" results from multiple Stata commands into a single
> column.  Specifically, I want to construct a k-column table for k
> related specifications of a model, where the first n1 rows for each
> specification (each column) list the parameter estimates and their
> SEs p-values from an e-class program (such as -ivreg2- or -nl-), the
> next n2 rows list the parameter estimates and SEs or p-values from a
> series of -nlcom- transformations based on the e-class estimates, and
> the final n3 rows report diagnostic statistics (e.g., sample size,
> AIC/BIC, etc.) from the e-class program.  I would like for this
> process to be automated, rather than involving cutting and pasting,
> with the goal of producing tables in both SMCL and LaTeX format.
>         I effect, I think I am looking for an "estimates combine" or
> "estimates merge" command:  the only way I have found to store the
> estimates from the -nlcom- commands (with their associated second
> moment statistics) is to use the -post- option, which for me creates
> a new estimate set rather than adding/appending to the existing one.
> I have a suspicion that it might be possible to cajole -estout- to
> give the table I am after, but I have not been successful.  (I can
> provide a lengthy set of examples of code I have tried to get what I
> am after, if necessary.)  I have Stata 10.  Any suggestions are most
> welcome.
>                                          -- Mike
> *
> *   For searches and help try:
> *
> *
> *
*   For searches and help try:

© Copyright 1996–2017 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index