Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: st: Probit Regression Model with many interaction terms
From
Tirthankar Chakravarty <[email protected]>
To
[email protected]
Subject
Re: st: Probit Regression Model with many interaction terms
Date
Mon, 29 Aug 2011 21:14:07 -0700
There is no inherent difficulty, as far as the Stata programming goes:
/******************************/
webuse union, clear
probit union i.south##(c.age c.grade i.not_smsa c.year)
margins, dydx(*)
/******************************/
Here the binary variable "south" is fully interacted with several
other variables. You should ideally decide for yourself whether you
want to include an interacted regressor as a (quasi-)continuous, or
factor variable, as in the -probit- regression above.
You might find all the materials relating to this topic on Maarten
Buis's website useful:
http://www.maartenbuis.nl/publications/interactions.html
T
On Mon, Aug 29, 2011 at 4:29 PM, Shu Zhang <[email protected]> wrote:
> Dear all,
>
> I am trying to run a probit regression model with more than one
> interaction term (STATA10).
>
> The dependent variable is a binary dummy "y"(y=1 or 0), on the right
> hand side, I interact all explanatory variables x1, x2, x3 with a
> female dummy (1 or 0) and want to get coefficients for these
> interaction terms.
>
> the OLS regression STATA codes are following:
>
> reg y x1 x2 x3 female x1_female x2_female x3_female
>
> note: there're three interaction terms in my model,
> x1_female=x1*female
> x2_female=x2*female
> x3_female=x3_female
> and x1, x2, x3 can be either continuous or dummy.
>
> Just wonder how to do this in a probit model.
>
> ps: I've tried "inteff" command, but 'inteff' seems dealing with the
> probit model with one interaction term, but not many.
>
> please let me know if anything unclear.
>
>
>
> best,
> --
> Shu Zhang
> Department of Economics
> University of Houston
> 248 McElhinney Hall
> Houston, TX 77204-5019
> *
> * 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/
>
--
Tirthankar Chakravarty
[email protected]
[email protected]
*
* 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/