Re: st: How to get marginal effect of quadratic term in tobit model in stata 11.0

[Maarten Buis <maartenlbuis@gmail.com>]

On Tue, Jul 19, 2011 at 1:05 AM, lutunnahar begum wrote:
> I tried the following command:
>
> gen tb2=tb^2
> tobit ch tb tb2 .........., ll(0) robust
> margins, dydx(*) predict (ystar (0,.)) post
>
> I also tried -dtobit- with -version 8.2- and got the 4 MEs  for squared term.
>
> I understand that the true ME should not consider the squared effect
> separately as there is only one variable. But papers using tobit model
> report the marginal effect of squared term. I am confused whether I
> should use the above mentioned command to get this.

Remember that squared terms are just interaction terms of a variable
with itself. In non-linear models the "marginal effect" of the product
term is meaningless, see Norton, Wang, and Ai (2004). So, the authors
in those papers that included the marginal effects of the interaction
terms made a mistake. There are ways of getting "correct" marginal
effects, but those are not worth the effort as they are likely to
confuse more than help. If you added a quadratic term than your
variable will have a non-linear effect, and the way to show that is
with graphs.

Hope this helps,
Maarten

Edward Norton, Hua Wang, and Chunrong Ai (2004) "Computing interaction
effects and standard errors in logit and probit models" The Stata
Journal 4(2):154--167.
<http://www.stata-journal.com/article.html?article=st0063>

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