--- On Sun, 8/2/09, Zohal Hessami <[email protected]> wrote:
> currently, I am dealing with ordered probit estimations
> where I want to investigate the effect of government size on
> people's life satisfaction. To do so I have interacted
> government size with a few institutional dummies such as the
> extent of corruption.
Are you sure you want to do interactions here. To me it would
make more sense to look at indirect effects: Part of the effect
of government size on life satisfaction occurs through
corruption, rather than the effect of government size changes
as the level of corruption changes. Anyhow these indirect
effects are also hard in non-linear models, see for example
Sinning, Mathias, Hahn, Markus and Bauer, Thomas K. (2008)
The Blinder–Oaxaca decomposition for nonlinear regression
models. The Stata Journal, 8(4): 480--492.
http://www.stata-journal.com/article.html?article=st0152 .
<snip>
> Is it possible that inteff can only be used for binary
> probit/logit and not for ordered probit/logit? If not, what
> else could be the reason why I get this error message?
If you type -help inteff- you will see that the title of this package is: "Computing interaction effects and standard errors in logit and probit models", so that indicates that you cannot do this after -oprobit-.
Hope this helps,
Maarten
-----------------------------------------
Maarten L. Buis
Department of Social Research Methodology
Vrije Universiteit Amsterdam
Boelelaan 1081
1081 HV Amsterdam
The Netherlands
visiting address:
Buitenveldertselaan 3 (Metropolitan), room N515
+31 20 5986715
http://home.fsw.vu.nl/m.buis/
-----------------------------------------
*
* 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/
