Three Essays on Estimation with Unpriced Amenities.

Abstract

Variation in the quality of job matches is an important determinant of workers' search decisions and the distribution of wages. I develop a structural search model that allows job match quality to depend on unpriced job amenities as well as monetary productivity, permitting match quality estimation that is robust to both unobserved amenities and selection. I estimate the model with wage and tenure data from the 1979 NLSY, finding that the standard deviation of job amenities is nearly as large as that of monetary productivity. I then use the model to investigate the welfare consequences of wage taxation and unemployment insurance. Traditional estimates of deadweight loss from wage taxation are increasingly overstated as job amenity dispersion rises.

Reported happiness provides a new way to evaluate unpriced goods and experiences. In the wake of important life events, measures of subjective well-being often exhibit considerable mean reversion, which has not been fully incorporated into the economic analysis of happiness. This can lead to bias when comparing events. In the second chapter, Miles Kimball, Daniel Silverman, and I provide a flexible, extensible econometric framework that accommodates adaptation and permits the comparison of happiness-relevant life events with dissimilar hedonic adaptation paths. The method is used to analyze a variety of events in the Health and Retirement Study panel.

The costly, endogenous supply of job amenities by firms has a number of interesting implications for labor markets and public policy. In the third chapter, Brendan Epstein and I show that it is necessary to estimate the heterogeneity and parameters of amenity supply in order to correctly infer deadweight loss from taxation. Deadweight loss is generally overestimated in work that omits explicit consideration of amenities, and this overestimation is proportional to the quantitative significance of heterogeneity in amenities across job matches. The endogenous supply of amenities, rather than exogenous endowment, is shown to exacerbate this overestimation. Examination of a static, non-search economy reveals that this is not just an artifact of search. Finally, we examine the dynamic response of taxable income and social welfare to unexpected tax changes.