As in Exercise 3.26 , use the cps09mar dataset and the subsample of white male Hispanics. Estimate the regression log(wage) 1 education2 experience3 experience2/1004.

As in Exercise 3.26

, use the cps09mar dataset and the subsample of white male Hispanics.

Estimate the regression loág(wage) Æ ¯1 educationů2 experienceů3 experience2/100ů4.

(a) Report the coefficient estimates and robust standard errors.

(b) Let µ be the ratio of the return to one year of education to the return to one year of experience for experienceÆ 10. Write µ as a function of the regression coefficients and variables. Compute bµ from the estimated model.

(c) Write out the formula for the asymptotic standard error for bµ as a function of the covariance matrix for b¯. Compute s(bµ) from the estimated model.

(d) Construct a 90% asymptotic confidence interval for µ from the estimated model.

(e) Compute the regression function at educationÆ 12 and experienceÆ 20. Compute a 95%confidence interval for the regression function at this point.

(f ) Consider an out-of-sample individual with 16 years of education and 5 years experience. Construct an 80% forecast interval for their log wage and wage. [To obtain the forecast interval for the wage, apply the exponential function to both endpoints.]