1

Both income and education are quantitative variables, while gender is of course categorical.

Can I find the linear regression for men and women separately, and then compare the coefficients for education?

After doing that, I want to use an interaction term.

Is this a sound method to test my question?

kjetil b halvorsen
  • 77,844
spicy_springroll
  • 71
  • This can and should all be done in one model from the start, you will then be able to compare all of these. – user2974951 Jan 09 '23 at 09:53
  • How could you possibly use an interaction if you start with two separate models? See https://stats.stackexchange.com/questions/373890/separate-models-vs-flags-in-the-same-model/373909#373909 – kjetil b halvorsen Jan 10 '23 at 03:56

0 Answers0