Stata The Stata listserver
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: Control function approach


From   "Kevin Amess" <Kevin.Amess@nottingham.ac.uk>
To   <statalist@hsphsun2.harvard.edu>
Subject   st: Control function approach
Date   Tue, 08 Nov 2005 20:57:03 +0000

Dear all,

I would very much appreciate some advice on applying the control function approach

I have 3 equations:

1. y1 = dZ + e

where y1 is a dicrete choice variable taking the value 1 if an MBO, 2 if an MBI, and zero is neither MBO or MBI. This is estimated by multinomial logit. Z the independent variable set.

My second equation:

2. wages = eemplyment + bX + aMBO + cMBI + v
3. employment = fW + u
a, b, c, d, e, and f are coefficients.

Equations 2 and 3 are estimated by 3SLS

My questions:
1. Can I use the multinomial logit in a control function approach?
2. If the answer to (1) is yes, can I use the fitted values from the multinomial logit as explanatory variables in equation (2) in order to test for endogeneity and correct the standard errors for bias? 
3. If the answer to (2) is no, is it possible to obtain the choice specific residuals from the multinomial logit? Wooldridge (2002) suggests using the residuals but I cannot find a way of obtaining them after multinomial logit estimation.

Any help on this is much appreciated.

Regards,
Kevin


This message has been checked for viruses but the contents of an attachment
may still contain software viruses, which could damage your computer system:
you are advised to perform your own checks. Email communications with the
University of Nottingham may be monitored as permitted by UK legislation.


*
*   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