I am updated with the recent advancements on appropriate methodologies to check for sig of interaction effects on probability.
I just want to know better the difference between
a. sig of an interaction effect on probability
versus
b. sig. of an interaction effect on a latent variable.
My problem is: I have some interaction coefficients which are sig; however, the inteff and other tests show that the interaction term has no sig effect on probability. Hence, I only have significance of an interaction coefficient, and can onluy interpret is as a sig effect on a latent variable.
If I interpret the interaction effects in terms of the effect on the latent variable, what does this exactly mean? What can I infer from this?
----- Messaggio originale -----
Da: "Martin Weiss" <[email protected]>
A: [email protected]
Inviato: Domenica, 10 gennaio 2010 22:07:13 GMT +01:00 Amsterdam/Berlino/Berna/Roma/Stoccolma/Vienna
Oggetto: st: AW: Interpreting interactions in probit and logit models
<>
Have you had a look at http://www.stata-journal.com/sjpdf.html?articlenum=st0063 ? Or http://www.stata-journal.com/article.html?article=st0178 ?
HTH
Martin
-----Ursprüngliche Nachricht-----
Von: [email protected] [mailto:[email protected]] Im Auftrag von [email protected]
Gesendet: Sonntag, 10. Januar 2010 22:01
An: [email protected]
Betreff: st: Interpreting interactions in probit and logit models
Dear Stata users,
if I have a significant interaction term in probit or logit model, how should I interpet it?
I have found this sentence: "as long as you interpret the interaction effects in terms of the effect on the latent variable you are ok in simply using the output from -probit- (i.e. the sig. of the coefficient); if you want to interpret the results in terms of the probabilit you should use -inteff-."
What is the difference between these two interpretations? In concrete terms: what can I say if I have a sig. interaction coefficient BUT THE INTERACTION EFFECT IS NOT SIGNIFICANT AFTER HAVING USED INTEFF OR RELATED POSTESTIMATIONS to check the effect on probability?? What are the specific conclusion I get from each of the two interpretations (on the latent variable and on the probability)?
(A final note (if it may help in the answer): I have this problem for two different regressions. In the firs regr, I have an interaction between "one dummy - one continuous" variables; in a second regression I have an interaction between two dummies).
*
* 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/
*
* 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/
*
* 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/
