Regress S on ASVABC, SM, and SF
Regress S on ASVABC, SM, and SF
Regress S on ASVABC, SM, and SF, where S is the number of years schooling, ASVABC is a measure of cognitive ability, SM is the respondent’s mother’s schooling years, SF is the respondent’s father’s schooling years, and MALE is a dummy variable that is 1 for male respondents and 0 for female ones. The following regression output is obtained.
| Source | SS df MS | Number of obs = 500
F( 4, 495) = 68.81 |
||||||
| Model | 91366.22524 4 341.55631 | Prob > F = 0.0000 | ||||||
| Residual | 2457.20676 495 4.96405406 | R-squared = 0.3573
Adj R-squared = 0.3249 |
||||||
| Total | 3823.432 499 7.66218838 | Root MSE = 2.228 | ||||||
| S | Coef. Std. Err. t P>|t| | [95% Conf. Interval] | ||||||
| ASVABC | 1.20327 | .1134408 10.61 0.000 | .9803849 | 1.426155 | ||||
| SM | .1745339 | .0475472 3.67 0.000 | .0811146 | .2679532 | ||||
| SF | .1121408 | .0412465 2.72 0.007 | .031101 | .1931807 | ||||
| MALE | -.8637231 | .2016953 -4.28 0.000 | -1.260007 | -.4674387 | ||||
| cons | 10.90114 | .5946959 18.33 0.000 | 9.7327 | 12.06958 | ||||
- Interpret the coefficients and perform t Is there any evidence that the educational attainment of males is different from that of females? [15 marks]
- Define
MASVABC = MALE × ASVABC,
and regress S on ASVABC, MALE, and MASVABC. The following results are obtained
Sˆ = 14.556 + 1.688ASVABC − 0.710MALE − 0.317MASVABC,
(0.152) (0.173) (0.211) (0.221)
P.T.O.
where the standard errors of parameter estimates are in brackets. Write down the fitted models for male and female respondents, respectively. Comment on whether education attainment models are different for males and females based on t statistics. [10 marks]
