Working Paper: NBER ID: w19369
Authors: Melvin Stephens Jr; Douyan Yang
Abstract: Causal estimates of the benefits of increased schooling using U.S. state schooling laws as instruments typically rely on specifications which assume common trends across states in the factors affecting different birth cohorts. Differential changes across states during this period, such as relative school quality improvements, suggest that this assumption may fail to hold. Across a number of outcomes including wages, unemployment, and divorce, we find that statistically significant causal estimates become insignificant and, in many instances, wrong-signed when allowing year of birth effects to vary across regions.
Keywords: Compulsory Education; Schooling Laws; Educational Attainment; Causal Estimates
JEL Codes: J24
Edges that are evidenced by causal inference methods are in orange, and the rest are in light blue.
| Cause | Effect |
|---|---|
| Compulsory schooling laws (I21) | Educational attainment (I21) |
| Educational attainment (I21) | Wages (J31) |
| Compulsory schooling laws (I21) | Wages (J31) |
| Compulsory schooling laws (I21) | Unemployment (J64) |
| Compulsory schooling laws (I21) | Divorce rates (J12) |
| Educational attainment (I21) | Log weekly wages (J31) |
| School quality measures (I21) | Wages (J31) |