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

Re: st: truncreg with panel data

From   Maarten buis <>
Subject   Re: st: truncreg with panel data
Date   Fri, 8 Feb 2008 10:57:55 +0000 (GMT)

--- Anita <> wrote:
> I would like to estimate a model based on Cragg (1971) which contains
> in a first step a probit estimation and in a second step a regression
> part for all positive outcomes of the probit estimation.
> I learned that I habe to estimate the second step with truncreg to 
> account for the truncation. 

First off all a quote from the statalist FAQ:

"Please do not assume that the literature familiar to you is familiar
to all members of Statalist. Do not refer to publications with just
minimal details (e.g., author and date). Questions of the form "Has
anyone implemented the heteroscedasticity under a full moon test of
Sue, Grabbit, and Runne (1989)?" admittedly divide the world. Anyone
who has not heard of the said test would not be helped by the full
reference to answer the question, but they might well appreciate the
full reference."

Second I very much doubt that -truncreg- is appropriate in your case
(but as you haven't given the appropriate reference I have not looked
it up). If you had truncation you would not be able to do the probit
you refered to, as your dataset would only consist of persons with (in
your case) positive outcomes. Apperently you have extra information
available: you also have data on respondents that do not a postive
value on the dependent variable. 

-- Maarten

Maarten L. Buis
Department of Social Research Methodology
Vrije Universiteit Amsterdam
Boelelaan 1081
1081 HV Amsterdam
The Netherlands

visiting address:
Buitenveldertselaan 3 (Metropolitan), room Z434

+31 20 5986715

Sent from Yahoo! Mail - a smarter inbox

*   For searches and help try:

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