Working Paper: NBER ID: w10809
Authors: Daniel S. Hamermesh; Stephen G. Donald
Abstract: We link information on the current earnings of college graduates from many cohorts to their high-school records, their detailed college records and their demographics to infer the impact of college major on earnings. We develop an estimator to handle the potential for non-response bias and identify non-response using an affinity measure -- the potential respondent's link to the organization conducting the survey. This technique is generally applicable for adjusting for unit non-response. In the model describing earnings, estimated using the identified (for non-response bias) selectivity adjustments, adjusted earnings differentials across college majors are less than half as large as unadjusted differentials and ten percent smaller than those that do not account for selective non-response.
Keywords: college curriculum; earnings; nonresponse bias
JEL Codes: J31; I21
Edges that are evidenced by causal inference methods are in orange, and the rest are in light blue.
| Cause | Effect |
|---|---|
| college curriculum (A22) | earnings (J31) |
| nonresponse bias (C83) | earnings differentials (J31) |
| high school performance (D29) | earnings (J31) |
| demographic characteristics (J21) | earnings (J31) |
| hours worked (J22) | earnings (J31) |
| upper-division science or math courses (C19) | earnings (J31) |
| college major (M39) | earnings (J31) |
| background factors (D91) | earnings differentials (J31) |