Interaction effects not significant

[Lynn Zhang]

Hi!

In my regression analysis, Asians earn more than Whites at a significant level (p<0.001), dummies for subjects taken at univerisity are included. To see whether Asians self-select into higher-paying subjects, I created an interaction term: asian_high_paying_subjects = asian * high_paying_subjects. The result shows that the interaction term is not significant, does it mean that they are not earning more because they did higher-paying subjects?

Many thanks for any help!
Lynn

[Carlo Lazzaro]

Lynn:
without sharing what you typed and what Stata gave you back (as per FAQ), my guess-work is simply that you can leave the interaction out.