Working Paper: NBER ID: w10146
Authors: Gadi Barlevy
Abstract: This paper proposes a methodology for estimating job search models that does not require either functional form assumptions or ruling out the presence of unobserved variation in worker ability. In particular, building on existing results from record-value theory, a branch of statistics that deals with the timing and magnitude of extreme values in sequences of random variables, I show how we can use wage data to identify the distribution from which workers search. Applying this insight to wage data in the NLSY dataset, I show that the data supports the hypothesis that the wage offer distribution is Pareto, but not that it is lognormal.
Keywords: No keywords provided
JEL Codes: F1; F3
Edges that are evidenced by causal inference methods are in orange, and the rest are in light blue.
| Cause | Effect |
|---|---|
| wage offer distribution identified as Pareto (D39) | higher wages associated with lower probabilities of occurrence (J31) |
| implicit record structure of job offers (J63) | identification of wage offers even amidst unobserved heterogeneity in worker ability (J31) |
| Burdett and Mortensen model of on-the-job search (J29) | equilibrium wage offer distribution contingent upon distribution of productivity across firms (J31) |