Bookmark and Share

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: Tobit interaction effect


From   Maarten Buis <maartenlbuis@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: Tobit interaction effect
Date   Thu, 10 May 2012 11:17:11 +0200

On Wed, May 9, 2012 at 10:31 PM, Ebru Ozturk wrote:
> I would like to measure the interaction effects as it is in OLS. My data is cross-sectional and dependent variable is censored. So, I guess I need to see the expected value of the observed value. I use Stata 10.

Not necessarily. Given that information I could just as easily justify
the interpretation in terms of the latent variable or the observed
values and the censored values fixed at the cut-off point.

As I said before: if you interpret your results in terms of the latent
variable you can just do what you would always do in a linear
regression(*). When you want the other interpretation you will need to
derive the cross partial derivatives yourself. Once you have done that
you can use -predictnl- to compute those effects and their standard
error for each observation.

-- Maarten

(*) Notice that OLS is just an algorithm while linear regression is
the model. I guess you mean the latter and not the former.

--------------------------
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/


© Copyright 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index