Statalist


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: st: Interaction with squared variable


From   rgutierrez@stata.com (Roberto G. Gutierrez, StataCorp)
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: Interaction with squared variable
Date   Tue, 13 Oct 2009 11:27:28 -0500

Giuseppe Cappelletti <giuseppe.cappelletti@gmail.com> has discovered a bug
when specifying interactions with squared terms in -oprobit-.  He writes:

> I would like to estimate an orderd probit model with the following
> specification:

> Prob(y=1) = x + a*gender + b*x + c*x^2 + d*gender*x^2

> I tried the following command:

> oprobit  y  ///
>    i.gender   ///
>    c.x   ///
>    c.x#c.x  ///
>    i.gender#(c.x#c.x)

> but it does not work. After the estimation I would like to compute the
> marginal effect (considering both the squared and interaction term).

This bug is triggered by the inclusion of both a squared term and its
interaction with a factor variable.  We will fix this in an update.

--Bobby
rgutierrez@stata.com
*
*   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/



© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index