Statalist


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

st: Hausman test for binary dependent variable and binary endogenous variable


From   "Sun, Yan (IFPRI)" <Y.SUN@CGIAR.ORG>
To   <statalist@hsphsun2.harvard.edu>
Subject   st: Hausman test for binary dependent variable and binary endogenous variable
Date   Sun, 9 Aug 2009 16:06:31 -0400

Hi,
I have two equations: 
1) Y1=b1*Y1+b2*X1+b3*X2+b4*X3
2) Y2=a1*X1+a2*Z1+a3*Z2
Where Y1 is binary dependent variable, Y2 is binary endogenous variable,
X1-X3 are exogenous variables, Z1 & Z2 are excluded exogenous variables,

1) First, I use "ivreg2 X1 X2 X3 (Y1=Z1 Z2)" to do relevance test and
overidentification test, even though Y1 and Y2 are binary variables, am
I right?
2) Later could I use "ivendog" after "ivreg2" to do hausman test even
though that Y1 and Y2 are binary variables?
3) If I use "robust" option after "ivreg2", how should I do housman
test?

Thank you for your help.
Yan

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/



© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index