I have a data set that has 6 observations per person. These relate to
each individual's behavior with respect to 6 different products. For
each observation, I have a binary variable for whether the person
purchased the product (my dependent variable) plus various time
varying and time-invariant independent variables. I'd like to estimate
a probit model using these data.
So the data look like:
ID Product1Purchase(1 or 0) varA1 VarA2 VarA3 VarB VarC
ID Product2Purchase(1 or 0) varA1 VarA2 VarA3 VarB VarC
.
.
ID Product6Purchase(1 or 0) varA1 VarA2 VarA3 VarB VarC
Using one of Nick's previous posts, my understanding is that the best
way to do this is to estimate a SUR model, by first estimating a
probit and then using the suest command is a postestimation command.
However, I don't quite understand how to do this. What is the
sequence ofcommands I should use?
Thanks,
Rachel
*
* 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/