Statalist


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

st: test for exogeneity


From   Dragutin Culinovic <dragutin.culinovic@fsb.hr>
To   STATA List <statalist@hsphsun2.harvard.edu>
Subject   st: test for exogeneity
Date   Wed, 01 Aug 2007 21:53:46 +0200

I have one Structural equation and two reduced form equations:

Structural: y=D1*g1 + D2*g2 + E1*b1 + E3*b3 + u
Reduced: D1=E1*p11 + E2*p21 + E3*p31 + E4*p41 + v1
D2=E1*p12 + E2*p22 + E3*p32 + E4*p42 + v2

(coefficients are in small letters)
y* is unobservable, and we observe only y (0 or 1)

E's are all exogenous, and D's are (supposed) endogenous.

u, v1 and v2 have a joint normal distribution with mean zero and finite positive covariance matrix. How can I find that matrix.

How can I compute residuals for each observation and add it to that observation row?

For test of exogeneity i must to use residuals v1 and v2 in Structural equation, joint with D's and E's, because probit statistic of v1 and v2 is a valid test of the null hypothesis that D's are exogenous.
How can I do this?

Thanks in advance.
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* 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