Re: st: Interaction effects

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

--- On Mon, 14/6/10, Lorenzo Ciari wrote:
> do you think that estimating a linear probability model
> would also be a solution?

That would give you an approximation of the marginal effects,
which is fine, but it has specific advantages and disadvantages
compared to odds ratios.

Don't forget to specify the -robust- option.

It will probably be OK as long as the predicted probabilities
don't get too close to either 0 or 1 (I have heared the rule
of thumb that the predicted probabilities should lie between
.2 and .8).

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/