Bookmark and Share

Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

RE: st: Explaining Gamma coefficient after bioprobit command

From   "Telli Anvernali Henry" <>
To   <>
Subject   RE: st: Explaining Gamma coefficient after bioprobit command
Date   Fri, 30 Apr 2010 15:37:44 +0100

Thanks for the response Maarten; My version of bioprobit was installed
using -findit bioprobit. This is written by Zurab Sajaia. When you run
it with the endogenous option, it reports a gamma which is not estimated
when you run the seemingly unrelated specification.


-----Original Message-----
[] On Behalf Of Maarten buis
Sent: 30 April 2010 11:21 AM
Subject: Re: st: Explaining Gamma coefficient after bioprobit command

--- On Thu, 29/4/10, Telli Anvernali Henry wrote:
> I am using the command bioprobit for my bivariate ordered
> probit regressions and I wondered if anybody can help me
> with an explanation for the estimated gamma beyond just
> the sign. I know rho measures the correlation of the error
> terms while gamma measure the actual relationship between
> equation 1 and 2 but apart from the sign of the gamma 
> coefficient what can I say about the impact of the coefficient
> itself and does it matter that gamma and rho have opposite
> signs? For instance if gamma is 0.64, what can I say apart
> from "there is a strong positive correlation between depvar1
> and depvar2".

-bioprobit- is a user written command, the Statalist FAQ askes
you to say where you got it from. This is crucial because there
are often multiple versions of a user written program floating
around cyber space. This appears to be the problem here, as
my version (downloaded from SSC by typing in Stata
-ssc install bioprobit-) does not return a gamma coefficient,
so there is nothing to interpret.

-- Maarten

. which bioprobit
*! version 1.11  17Aug2007

Maarten L. Buis
Institut fuer Soziologie
Universitaet Tuebingen
Wilhelmstrasse 36
72074 Tuebingen


*   For searches and help try:
This message has been checked for viruses but the contents of an attachment
may still contain software viruses which could damage your computer system:
you are advised to perform your own checks. Email communications with the
University of Nottingham may be monitored as permitted by UK legislation.
*   For searches and help try:

© Copyright 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index