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

st: Re: Heckman Sample Selection and Average treatment Effect

From   jean ries <>
Subject   st: Re: Heckman Sample Selection and Average treatment Effect
Date   Thu, 17 Jun 2004 10:47:18 +0200

At 22:57 16/06/2004, you wrote:
Dear Friends,

I am doing a research on identifying the average treatment effect of a training program. In order to get rid of the endogeneity problem of program participation, I want to try Heckman sample selection technique. But I don't know how to get the average treatment effect by running Heckman in Stata.

For example,

t is dummy for training program (1: participate, 0: not participate)

I want to know how much the training program improve the performance.

The command
heckman dep_var var_1...var_n (t=var_1...var_m) twostep
can not give me the effect of t on dep_var.

How can I do that in Stata?
I think that -treatreg- is doing what you want.

. treatreg dep_var var_1...var_n , treat(t=var_1...var_m) twostep

Also have a look at the following FAQ:


*   For searches and help try:

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