Statalist The Stata Listserver

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

Re: st: Re: Basic question on "estimates"

From   "Pancho Villa" <[email protected]>
To   [email protected]
Subject   Re: st: Re: Basic question on "estimates"
Date   Tue, 26 Sep 2006 15:42:35 -0400

The problem with "statsby" is that if the regression is weighted, it
doesn't work.  And my regressions are weighted.  It seems that
"statsby" works with plain vanilla OLS regressions, but not for other
procedures I'm using.

Thanks for the replies.


On 9/26/06, Michael Blasnik <[email protected]> wrote:

In addition to the other reply, you may want to check out -statsby- to
create a dataset of results.

Michael Blasnik

----- Original Message -----
From: "Pancho Villa" <[email protected]>
To: <[email protected]>
Sent: Tuesday, September 26, 2006 3:26 PM
Subject: st: Basic question on "estimates"

>I browsed the list archives for an answer to this.  Unfortunately, the
> related material I found was too advanced for my limited Stata skills
> and my little problem:
> I'm using the "by" command to sub-sample my data and run a bunch of
> regressions (hundreds) and I'm interested in listing (as columns
> indexed by my "by" variable) the estimated coefficients, the t values
> of some of the regressors, and the adj-R2s in a text format so that I
> can open them with Excel, etc.  That's it.
> I cannot use "estimate store" because it only saves the estimates of
> the last regression.  I don't want to run each regression separately
> to be able to store each set of estimates and then tabulate them all.

*   For searches and help try:

*   For searches and help try:

© Copyright 1996–2024 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index