Dear statalisters,
i am a new member of the list and in need of your help in obtaining K.M.
Murphy and R.H. Topel's (1985) asymptotic variance-covariance matrix so as
to conduct a statistical significance test in a dichotomous probit model and
in a negative binomial model.
The models I work with are bivarite probits defined in the following:
Y1i = Xi*beta + ui
Y2i = Xi*gamma + uihat*lambda + ei
where Y1i is insurance coverage choice and Y2i is the presence/absence of
car accidents. The key is to determine the statistical significance of
lambda for uihat in the second equation while using Murphy and Topel's
(1985) asymptotic variance-covariance matrix.
Alternatively, I also define Y2i in the second equation as a count of
accidents instead of a dummy. In this case, should I have to follow
different procedures to test the statistical significance with Murphy and
Topel's (1985)? If so, how?
I thank you for the help in advance.
hyojoung
Hyojoung Kim
Assistant Professor of Sociology
University of Washington
202 Savery Hall, Box 353340
Seattle, WA 98195-3340
(Phone) 206-543-9644
(Fax) 206-543-2516
(E-mail) [email protected]
*
* 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/
