"Guillaume Frechette" <[email protected]> wrote:
> Dear Statalisters, I am estimating a random effects probit: y =
> 1{A + BX + e
> >= 0} and my estimated values are a and b (and rho but forget about that
> last one). I need to test the null hypothesis that a>0 and a+b<0. I have
> never performed a joint hypothesis test with inequalities, but I
> have read
> that the usual Wald test is inappropriate because it treats positive and
> negative misses symmetrically. Apparently, Wolak (`An Exact Test for
> Multiple Inequality and Equality Constraints in the Linear Regression
> Model', Journal of the American Statistical Association, Vol 82,
> Issue 399,
> Sep. 1987, pp. 782-793) derives such a test for the linear
> regression model.
> I would like to know:
>
> 1. As anybody programmed such a test (if so would you be so kind
> as to share
> your program).
>
> and/or
>
> 2. Do you know of a reference for such a test in the case of
> something like
> a random effects probit.
>
> and/or
>
> 3. Do you have any references that might help or any advice
> suggestions, etc
> that could help.
This can be bootstrapped, without any programming, using the -bs- command.
Using the auto data set (& changing the hypothesis slightly),
the following will do it:
bs "xtprobit foreign weight, re i(rep78)"
"(_b[_cons]>0)&(_b[_cons]+_b[weight]<4)"
I trust that your application makes more sense than this one.
Adapt as necessary. No spaces are permitted when describing
the hypotheses to be tested. A reps option is needed.
See help for the command -bs- for more details, inclusing the meanings of
the difference confidence intervals.
*
* 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/
