Hello all,

I have been looking for days for an answer to this question, but have not found an answer so far.

My problem is as follows: I am working on a project where I am looking to see if sexual minorities (gay men/lesbian women) are more likely to enter male dominated industries. I have computed dummy variables (1/0) for the sexual minorities, and created dummies for male dominated industries (i.e. a dummy for industries that are 0-20% male, a dummy for industries that are 20-40% male etc.). I have an (unbalanced) panel data set, so I am using the xtlogit command (with odds ratio) to see whether sexual minorities are more likely to enter certain industries. However, when I use the command xtlogit (with 0-20% male dominated as dependent variable) and sexual minority as independent variable, the odds ratio I get is 2.82e-07 - which seems unlikely, as a substantial amount of sexual minorities are working in this industry.

What am I missing?

Kind Regards,

Bob Schuitemaker