The joint relationship between two categorical variables can be addressed using -glm- or -poisson- to fit loglinear models.
Nick
[email protected]
nigussie Tefera
(a) I have two dependent variables (both dummy variables): one has two categories ( 0 and 1) and the second dependent variable has three categories (0, 1, and 2). Is it possible to estimate the joint relationship betwees these two dependent variables using the biprobit command?
(b) Note: I run the regression and STATA provided some results. I wanted to make sure with you whether this is reliable becuse STATA Help states the biprobit command is used to run two-equation probit models.
(c) If it is possible, and the output from (a) is reliable, how would one interpret the estimation results for the dependent variable has three categories (0, 1, and 2)?
*
* 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/
