Stata The Stata listserver
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: RE: behaviour of -estout- w/ -oprobit-

From   "Jann Ben" <>
To   <>
Subject   st: RE: behaviour of -estout- w/ -oprobit-
Date   Wed, 28 Sep 2005 10:01:03 +0200

Radu had problems using -estout- with -oprobit-. -oprobit- is a 
multiple equation command (the cutoff parameters are put into 
separate equations) and -estout- therefore tries to match 
equations by name. Since the dependent variable in Radu's models 
differs, each model will have its own coefficients block in the 
table produced by -estout-. Furthermore, the -keep()- option 
as specified by Radu only keeps coefficients from the first block. 

The solution to the problem is to add -equations(1)- to the 
-estout- command. Thus, Radu's command should read

.  estout ff_* using `mydir'\state_eff_freq.txt, eq(1) ...


Radu wrote:
> I am using -estout- to put together the results of a set of ordered
> probits. Specifically, the relevant part of my dofile looks like this:
> ....
> foreach v of local list1 {
> 	oprobit `v' AP KA TN, cluster(keyid)
> 	estimates store ff_`v'
> }
> estout ff_* using `mydir'\state_eff_freq.txt, cells(b(star fmt(%9.3f))
> se(par)) keep(AP KA TN) stats(r2_p N, fmt(%9.3f %9.0g)
> labels(psR-squared)) style(tab) replace
> ....
> However, in the output file, only the first column of results is
> shown, the other remaining blank. I know for sure that the ordered
> probits run fine for all my dependent variables so I'm thinking the
> problem lies within -estout-. Furthermore, when I am using -estout-
> with regular probits (for a different set of dependent variables), I
> can collect the results just fine ...

*   For searches and help try:

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