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

Re: st: info on treatment effects model

From   "Austin Nichols" <>
Subject   Re: st: info on treatment effects model
Date   Fri, 31 Aug 2007 09:59:06 -0400

You can use -ivreg2- or -ivregress-; the fact that the endogenous
variable/s is/are binary does not affect consistency of the IV
estimator, and you can generate new instruments to improve efficiency
(but beware of pernicious weak instruments problems). See e.g. pages
49-50 of

On 8/31/07, Luca Tiberti <> wrote:
> I have a model where the dependent variable is continuous and more than one
> regressor endogenous and binary. I know that with only one endogenous
> regressor I should use the command "treatreg"; which command is suitable
> with more than one endogenous binary regressor?
*   For searches and help try:

© Copyright 1996–2015 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index