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]

st: Tests of Instruments after -ivreg2-

From   Danny Dan <>
Subject   st: Tests of Instruments after -ivreg2-
Date   Mon, 14 May 2012 02:45:48 -0500

Dear Friends,

I have two questions related to the tests of instrumental variables
(IVs) after -ivreg2-:

(1) I have a model where the response variable (y1) is binary. Also
the endogenous explanatory variable (y2) and the instruments are
binary. In this case, can I use ivreg2 in order to test my IVs. Are
the test results as will be obtained using -ivreg2- would be
appropriate (correct) in my case (when I have both y1 and y2 as binary

(2) Can I use ivreg2 when y1 (response variable) is censored and y2
(endogenous explanatory variable) is binary?

I am thinking of using -ivreg2- as it provides rich set of tests for IVs.

Please let me know if my questions need clarification.

I will appreciate your help.

Thank you for your time.


*   For searches and help try:

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