(Stata) The Determinants of Wages.

Card (1995) used wage and education data for a sample of men in 1976 to estimate the return to education. He used a dummy variable for whether someone grew up near a four-year college (nearc4) as an instrumental variable for education.

The data in CARD.RAW3contains a sample of 3,010 men. We are going to use the following variables:lwage(log wages),exp(experience),black(an indicator for race),south(an indi- cator for residency in the South),south66(an indicator for residency in the South in 1966),smsa(an indicator for residency in a metropolitan area),smsa66(an indicator for residency in a metropolitan area in 1966) andreg661-reg669(regional dummies).

Consider the following regression equation for the wage equation:

ln(wage)i=educi+TXi+i i=1,...,N (1)

whereln(wage)iis log wages,educiis schooling andXi= (expi,exp2i,blacki,southi,south66i,smsai,smsa66i, regional dummies)T

. Notice that a constant is not included because it would be collinear with the regional dummies.

Estimate the regression equation (1) using OLS and report the coefficientsand(no2

need to report the regional dummies), standard errors andR. Do you think thatmay be biased in this model? Explain.

My question is what is the command line in Stata to perform this regression?