Re: st: "cmp" command and rho LR test statistic for SUR bivariate probit model

[Maarten buis <maartenbuis@yahoo.co.uk>]

--- On Mon, 28/2/11, David Quinn wrote:
> Is there any way to compute the likelihood-ratio chi-square
> test statistic regarding correlation of error coefficients
> (i.e., that rho=0) when using David Roodman's "conditional 
> mixed process" (aka "cmp") module to estimate a seemingly
> unrelated bivariate probit model? 

Yes, I just wrote a Stata tip for that, which will appear in
the Stata Journal 11(2). A pre-publication draft can be seen
here: <http://www.maartenbuis.nl/publications/sigma_rho.html>.

Below is an example that applies the general idea of that tip
to -cmp- (which I got from SSC by typing in Stata 
-ssc install cmp, replace- and -ssc install ghk2, replace-.)

*------------- begin example -----------
cmp setup
webuse laborsup, clear
replace fem_inc = fem_inc - 10
cmp (kids = fem_inc male_educ) ///
    (fem_work = male_educ),    ///
    ind($cmp_cont $cmp_cont)   ///
    quietly
est store a

constraint 1 [atanhrho_12]_cons = `=atanh(0)'
cmp (kids = fem_inc male_educ) ///
    (fem_work = male_educ),    ///
    ind($cmp_cont $cmp_cont)   ///
    quietly constraint(1)
est store b

lrtest a b
*------------- end example -----------------
(For more on examples I sent to the Statalist see: 
http://www.maartenbuis.nl/example_faq )

Hope this helps,
Maarten

--------------------------
Maarten L. Buis
Institut fuer Soziologie
Universitaet Tuebingen
Wilhelmstrasse 36
72074 Tuebingen
Germany

http://www.maartenbuis.nl
--------------------------


      

*
*   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/