We considered a Hausman and Taylor (1981) estimator for a static earnings equation using the study of Cornwell and Rupert (1988); see Table 7.5. This used data on 595 individuals drawn from the PSID for the period 1976-1982. Using this data estimate a dynamic version of this earnings equation using the Kripfganz and Schwarz (2018) twostep estimator. Are the results sensitive to introducing dynamics? Is the lagged dependent variable significant? What is the returns to schooling? Do females make less than males and is that significant?

Table 7.5:

 

Transcribed Image Text:

GLS Within HT AM 4.264 2.913 2.927 Constant (0.098) (0.284) (0.275) 0.0010 0.0008 0.0008 0.0008 WKS (0.0008) (0.0006) (0.0006) (0.0006) -0.017 -0.002 0.007 0.007 SOUTH (0.027) (0.034) (0.032) (0.032) -0.014 -0.042 -0.042 -0.042 SMSA (0.020) (0.019) (0.019) (0.019) -0.075 -0.030 -0.030 -0.030 MS (0.023) (0.019) (0.019) (0.019 0.082 0.113 0.113 0.113 EXP (0.003) (0.002) (0.002) (0.002) -0.0008 -0.0004 -0.0004 -0.0004 EXP (0.00006) (0.00005) (0.00005) (0.00005) -0.050 -0.021 -0.021 -0.021 (0.017) (0.014) (0.014) (0.014) 0.004 0.019 0.014 0.014 IND (0.017) (0.015) (0.015) (0.015) 0.063 0.033 0.033 0.032 UNION (0.017) (0.015) (0.015) (0.015) -0.339 -0.131 -0.132 FEM (0.051) (0.127) (0.127) -0.210 -0.286 -0.286 BLK (0.058) (0.156) (0.155) 0.100 0.138 0.137 ED (0.006) (0.021) (0.021) x=5075 x=5.26 X=14.74