Working Paper: NBER ID: w12018
Authors: James J. Heckman; Paul A. Lafontaine
Abstract: Using three sources of data, this paper examines the direct economic return to GED certification for both native and immigrant high school dropouts. One data source - the CPS - is plagued by non-response and allocation bias from the hot-deck procedure that biases upward the estimated return to the GED. Correcting for allocation bias and ability bias, there is no direct economic return to GED certification. An apparent return to GED certification with age found in the raw CPS data is due to dropouts becoming more skilled over time. These results apply to native born as well as immigrant populations.
Keywords: No keywords provided
JEL Codes: C61
Edges that are evidenced by causal inference methods are in orange, and the rest are in light blue.
| Cause | Effect |
|---|---|
| allocation bias + ability bias (J71) | GED certification return (D50) |
| GED certification (C68) | wages (J31) |
| dropouts (I21) | GED certification return (D50) |
| GED recipients (no college) (I23) | wages (same as uncertified dropouts) (J39) |
| positive wage differences (unadjusted CPS) (J31) | unobserved ability bias + improper allocation of GED missing wages (J79) |
| selection bias (C24) | positive estimates of GED effects (I26) |
| ability accounted for (M41) | negligible returns to GED certification (I26) |