Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down on April 23, and its replacement, statalist.org is already up and running.


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: st: Interaction terms


From   josephine gakii <jogakii@yahoo.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: Interaction terms
Date   Thu, 7 Apr 2011 01:55:38 -0700 (PDT)

Thanks Marteen and the rest for the replies to these thread.

yes i used the official Stata program -mprobit-. Because my error terms are correlated i settled on -mprobit- which has four categories in the dependent variable . 

i concur with Marteen that i have to use the delta method which gives the difference in the predicted probabilities. Unfortunately i am not conversant with the proposed -asmprobit-. could anyone please explain to me the -asmprobit-? 

again, does this imply i cannot use the delta method after running the -mprobit- command? i am also interested in understanding how the -predictnl- and -nlcom- commands work given that when i run my -mprobit- (assuming it is justified to use it) i get results in three categories (  the dependent variable has four categories); since the predictnl is on each variable, how can i extract the predictions of each variable in each of the three different categories of my dependent variable?

thanks
Josephine

--- On Mon, 4/4/11, josephine gakii wrote:
> I am using multinomial probit with an interaction term in
> it. I would like to compute standard errors for meaningful
> interpretation of my results that have an interaction
> term.  
> 
> I have tried using the -inteff- command in STATA but it
> seems to support only the binary logit and probit. i have
> also tried the CLARIFY command in STATA but it does not
> support multinomial probit 
> 
> Is there a command that can handle interaction terms in
> multinomial probit? 

I am assuming you used the official Stata program -mprobit-.
In that case there isn't much added value of using -mprobit-
over using -mlogit-, as the error terms are assumed to be
uncorrelated. If this does not worry you, than I would go
for -mlogit- and interpret the relative risk ratios as 
discussed in: 

M.L. Buis (2010) "Stata tip 87: Interpretation of interactions
in non-linear models", The Stata Journal, 10(2), pp. 305-308.

If you want to include correlated error terms, then you 
first need to think about identification, e.g. through 
alternative specific variables as implemented in -asmprobit-.
After that you'll probably need to compute the appropriate
marginal effects for the interaction terms manually using
either -nlcom- or -predictnl-. Those programs will than compute
the standard errors (using the delta method) for you.

Hope this helps,
Maarten

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




*
*   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 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index