EXERCISE 2 Consider the following model: Y. =-0.261-2.360D, -1.732D, +2.128DD, +0.802X Where Y earnings, X = education, D1=1 if female, 0 otherwise; D2=1 if non-white and non- Hispanic, =0 otherwise. All the coefficients are statistically significant. a- Test the hypothesis that earnings differ by gender when D2=1. b- Test the hypothesis that earnings differ by race when D1=1. c- How would your results above change if the coefficient on the interaction variables were non-significant? What conclusion do you draw on the role of the interactive dummy