Suppose that instead of the model inc; = Be + B, ed; + B2 sex, + &i (sex equals 1 for males and 0 for females) we posited inc; = 20 + a, ed, + a2 sexi + ei = 365 where sex* equals 0 for males and 1 for females. What would you expect concerning the relationship between the parameter estimates and the interpretation of these estimates from OLS regressions of these alternative formulations?
