Dear List,
I try to estimate the interaction effect between two variables in a logit model.
My model looks like this: Pr(y) = x1 + x2 + x1*x2 + X
x1 is a continuously variable, x2 is a dummy variable in some specifications, in others it is a continuously variable. x1*x2 is the interaction effect, X are several control variables.
To obtain the correct interaction effect, I use the inteff command provided as an ado-file by Norton, Wang, and Ai (2004) "Computing interaction effects and standard errors in logit and probit models", The Stata Journal 4, Number 2, pp. 154-167.
Unfortunately, in some specifications the inteff command doesn't work and displays following error message:
conformability error
r(503);
This problem was on statalist in April 2006, but as far as I see there was no solution provided. (see http://statacorp.com/statalist/archive/2006-04/msg00364.html). Does anybody have an idea how to solve my problem?
Thank you for your help!
Jochen
---
Jochen Sp�th
Dipl.-Volkswirt
Institut f�r Angewandte Wirtschaftsforschung (IAW) T�bingen
Ob dem Himmelreich 1
72074 T�bingen
Tel.: 07071/9896-14
Fax : 07071/9896-99
EMail: [email protected]
IAW-Homepage: www.iaw.edu
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/