It is common practice to use sensible rules of thumb for cleaning data. Measurement error is often the justification for removing (trimming) or recoding (winsorizing) observations where the dependent variable has values that lie outside a specified range. We consider a general measurement error process that nests many plausible models. Analytic results demonstrate that winsorizing and trimming are solutions for a narrow class of error processes. Indeed such procedures can induce or exacerbate bias. Monte Carlo simulations and empirical results demonstrate the fragility of cleaning. Even on root mean square error criteria, we cannot find generalizable justifications for these procedures.

We use admissions lotteries to estimate the effects of attendance at Boston's charter high schools on college preparation, college attendance, and college choice. Charter attendance increases pass rates on the high-stakes exam required for high school graduation in Massachusetts, with especially large effects on the likelihood of qualifying for a state-sponsored college scholarship. Charter attendance has little effect on the likelihood of taking the SAT, but shifts the distribution of scores rightward, moving students into higher quartiles of the state SAT score distribution. Boston's charter high schools also increase the likelihood of taking an Advanced Placement (AP) exam, the number of AP exams taken, and scores on AP Calculus tests. Finally, charter attendance induces a substantial shift from two-to four-year institutions, though the effect on overall college enrollment is modest. The increase in four-year enrollment is concentrated among four-year public institutions in Massachusetts. The large gains generated by Boston's charter high schools are unlikely to be generated by changes in peer composition or other peer effects.

In the context of certain dynamic models, it is possible to infer the elasticity of labor supply to the firm from the elasticity of the quit rate with respect to the wage. Using this property, we estimate the average labor supply elasticity to public school districts in Missouri. We leverage the plausibly exogenous variation in prenegotiated district salary schedules to instrument for actual salary. These estimates imply a labor supply elasticity of about 3.7, suggesting that school districts possess significant market power. The presence of monopsony power in this teacher labor market may be partially explained by its institutional features.

Chile is unusual in having long-term experience with nationwide school vouchers. A key criticism of school voucher systems is that they make it easier for private schools to attract better teachers to the detriment of public schools. This paper uses longitudinal data from Chile to estimate a discrete choice dynamic programming (DCDP) model of teacher and nonteacher labor supply decisions and to explore how wage policies affect the composition of the teacher labor force in public and private schools. In the model, individuals first decide whether to get a teaching degree and then choose annually from among five work/home sector alternatives. Empirical results show that private voucher schools attract better teachers than public schools. However, the existence of the private voucher sector also draws higher-productivity individuals into the teaching profession.

Pre-College human capital investment occurs within a competitive environment and depends on market incentives created by Affirmative Action (AA) in college admissions. These policies affect mechanisms for rank-order allocation of college seats, and alter the relative competition between blacks and whites. We present a theory of AA in university admissions, showing how the effects of AA on human capital investment differ by student ability and demographic group. We then conduct a field experiment designed to mimic important aspects of competitive investment prior to the college market. We pay students based on relative performance on a mathematics exam in order to test the incentive effects of AA, and track study efforts on an online mathematics website. Consistent with theory, AA increases average human capital investment and exam performance for the majority of disadvantaged students targeted by the policy, by mitigating so-called "discouragement effects." The experimental evidence suggests that AA can promote greater equality of market outcomes and narrow achievement gaps at the same time.

This article studies how decentralization of wage bargaining from sector to firm level influences wage levels and wage dispersion. We use detailed panel data covering a period of decentralization in the Danish labor market. The decentralization process provides variation in the individual worker’s wage-setting system that facilitates identification of the effects of decentralization. We find a wage premium associated with firm-level bargaining relative to sector-level bargaining and that the return to skills is higher under the more decentralized wage-setting systems. Using quantile regression, we also find that wages are more dispersed under firm-level bargaining compared to more centralized wage-setting systems.

We present new estimates of earnings volatility over time and the life cycle for men and women by race and human capital, using Social Security earnings linked to the Current Population Survey. From the late 1970s to the mid-1990s, there is a strong negative trend in earnings volatility driven by a decline in transitory variance. From the mid-1990s, there is relative stability in trends of male earnings volatility due to an increase in the variance of permanent shocks. Cohort analyses indicate that earnings volatility is U-shaped, driven by large permanent shocks early and later in the life cycle.