Suppose that the values %1 and 1 are used for the dummy regressor D in Equation 7.1 instead of 0 and 1. Write out the regression equations for men and women, and explain how the parameters of the model are to be interpreted. Does this alternative coding of the dummy regressor adequately capture the effect of gender? Is it fair to conclude that the dummy-regression model will ‘‘work’’ properly as long as two distinct values of the dummy regressor are employed, one each for women and men? Is there a reason to prefer one coding to another?
Already registered? Login
Not Account? Sign up
Enter your email address to reset your password
Back to Login? Click here