Statalist


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

st:ivreg2 (with orthog option)


From   Mohamed Lajnef <Mohamed.lajnef@inserm.fr>
To   statalist@hsphsun2.harvard.edu
Subject   st:ivreg2 (with orthog option)
Date   Wed, 22 Oct 2008 14:40:07 +0200

Dear statalisters,

I am a new user of IV methods and I would be grateful if you would help me.

I want to test whether a particular variable, bmi,  is exegenous, so i run
ivreg2 Y bmi (=VARiv), orthog(bmi) is that correct?

I get the following statistics
------------------------------
------------------------------------------------
mah4 | Coef. Std. Err. z P>|z| [95% Conf. Interval]
-------------+----------------------------------------------------------------
bmi | -.176151 .0587376 -3.00 0.003 -.2912745 -.0610274 _cons | 50.08047 1.457251 34.37 0.000 47.22431 52.93663
------------------------------------------------------------------------------
Sargan statistic (Lagrange multiplier test of excluded instruments): 23.173 Chi-sq(1) P-val = 0.0000
-orthog- option:
Sargan statistic (eqn. excluding suspect orthogonality conditions): 0.000 Chi-sq(0) P-val = . C statistic (exogeneity/orthogonality of suspect instruments): 23.173 Chi-sq(1) P-val = 0.0000
Instruments tested:   bmi
------------------------------------------------------------------------------
Included instruments: bmi
Excluded instruments: fto
------------------------------------------------------------------------------


Questions:

1) the C stat shows  that bmi is endogenous and IV method is appropriate?

2)the Sargan stat confirms that VARiv is endogenous? and how to interpret the orthog-option in this example ?


Thanks in advance
Mohamed
*
*   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