Journal of Econometrics最新文献

We document substantial variation in the effects of a highly-effective literacy program in northern Uganda. The program increases test scores by 1.4 SDs on average, but standard statistical bounds show that the impact standard deviation exceeds 1.0 SD. This implies that the variation in effects across our students is wider than the spread of mean effects across all randomized evaluations of developing country education interventions in the literature. This very effective program does indeed leave some students behind. At the same time, we do not learn much from our analyses that attempt to determine which students benefit more or less from the program. We reject rank preservation, and the weaker assumption of stochastic increasingness leaves wide bounds on quantile-specific average treatment effects. Neither conventional nor machine-learning approaches to estimating systematic heterogeneity capture more than a small fraction of the variation in impacts given our available candidate moderators.

In a successful transition from youth to adulthood, individuals pass through a sequence of roles involving school, work, and family formation that culminate in their becoming self-sufficient adults. However, some “disconnected” youth spend extended periods of time outside of any role that constitutes an element of the pathway towards adult independence. Assisting these youth requires a systematic understanding of what “disconnection” means, how many disconnected youth there are, who these youth are, and how the scale of the problem has evolved over time. Using the National Longitudinal Surveys of Youth for 1997 and 1979, we address these issues by creating concrete definitions of “disconnection spells” using rich data on youths’ enrollment, work, and personal histories. We estimate a multi-state duration model to account for right censoring and to understand differences across salient sub-groups. Our estimates imply that in the early 2000s, almost 19% and 25% of young men and young women, respectively, experienced a disconnection spell by age 23 using our basic definition. These rates are substantially higher for certain sub-groups defined by race/ethnicity, parental education, and government aid receipt, rising as high as 30+% by age 23. Approximately 60% of youth with a disconnection spell have it last longer than a year, and close to 10% have it last longer than 4 years. However, once reconnected, a majority of youth go at least three years without a re-disconnection spell. Patterns of initial disconnection changed markedly from the 1980s to the 2000s, as young women saw a 12 percentage point decline over time. Moreover, the Black-White gap in disconnection has fallen for women, but increased for men. Our profile of disconnection experiences provides a starting point for government agencies aiming to understand where, how, and with whom to intervene to prevent lengthy disconnection spells.

Recent estimates are that about 150 million children under five years of age are stunted, with substantial negative consequences for their schooling, cognitive skills, health, and economic productivity. Therefore, understanding what determines such growth retardation is significant for designing public policies that aim to address this issue. We build a model for nutritional choices and health with reference-dependent preferences. Parents care about the health of their children relative to some reference population. In our empirical model, we use height as the health outcome that parents target. Reference height is an equilibrium object determined by earlier cohorts’ parents’ nutritional choices in the same village. We explore the exogenous variation in reference height produced by a protein-supplementation experiment in Guatemala to estimate our model’s parameters. We use our model to decompose the impact of the protein intervention on height into price and reference-point effects. We find that the changes in reference points account for 65% of the height difference between two-year-old children in experimental and control villages in the sixth annual cohort born after the initiation of the intervention.

This paper develops a partial-identification methodology for analyzing self-selection into alternative compensation schemes in a laboratory environment. We formulate a model of self-selection in which individuals select the compensation scheme with the largest expected valuation, which depends on individual- and scheme-specific beliefs and non-monetary preferences. We characterize the resulting sharp identified sets for individual-specific willingness-to-pay, subjective beliefs, and preferences, and develop conditions on the experimental design under which these identified sets are informative. We apply our methods to examine gender differences in preference for winner-take-all compensation schemes. We find that what has commonly been attributed to a gender difference in preference for performing in a competition is instead explained by men being more confident than women in their probability of winning a future (though not necessarily a past) competition.

Applied researchers using structural models under rational expectations (RE) often confront empirical evidence of misspecification. In this paper we consider a generic dynamic model that is posed as a vector of unconditional moment restrictions. We suppose that the model is globally misspecified under RE, and thus empirically flawed in a way that is not econometrically subtle. We relax the RE restriction by allowing subjective beliefs to differ from the data-generating probability (DGP) model while still maintaining that the moment conditions are satisfied under the subjective beliefs of economic agents. We use statistical measures of divergence relative to RE to bound the set of subjective probabilities. This form of misspecification alters econometric identification and inferences in a substantial way, leading us to construct robust confidence sets for various set identified functionals.

This paper examines the econometric causal model and the interpretation of empirical evidence based on thought experiments that was developed by Ragnar Frisch and Trygve Haavelmo. We compare the econometric causal model with two currently popular causal frameworks: the Neyman–Rubin causal model and the Do-Calculus. The Neyman–Rubin causal model is based on the language of potential outcomes and was largely developed by statisticians. Instead of being based on thought experiments, it takes statistical experiments as its foundation. The Do-Calculus, developed by Judea Pearl and co-authors, relies on Directed Acyclic Graphs (DAGs) and is a popular causal framework in computer science and applied mathematics. We make the case that economists who uncritically use these frameworks often discard the substantial benefits of the econometric causal model to the detriment of more informative analyses. We illustrate the versatility and capabilities of the econometric framework using causal models developed in economics.

This paper develops and estimates a two-factor model of intergenerational skill transmission when earnings inequality reflects differences in individual skills and other non-skill shocks. We consider heterogeneity in both initial skills and skill growth rates, allowing variation in skill growth to change over the lifecycle. Using administrative tax data on two linked generations of Canadians covering 37 years, we exploit covariances in log earnings (at different ages) both across and within generations to identify and estimate the intergenerational correlation structure for initial skills and skill growth rates, lifecycle skill growth profiles, and the dynamics of non-skill earnings shocks.

We estimate low intergenerational elasticities (IGEs) for earnings in Canada; however, skill IGEs are typically 2–3 times larger due to considerable (and persistent) variation in earnings conditional on skills. Both earnings and skill IGEs decline for more recent child cohorts and are lower for children born to younger fathers. Intergenerational transmission of both initial skills and skill growth rates explains up to 40% of children’s skill variation. Skills become a more important determinant of earnings over the first part of workers’ careers; however, intergenerational transmission of skills becomes less important as children age, because skill growth rates are not well-predicted by parental skills. Parents’ initial skills and skill growth rates are equally important determinants of children’s skills, largely because both strongly influence children’s initial skills.

Finally, we study intergenerational mobility for the 35 largest cities in Canada, documenting the extent to which considerable differences in earnings and skill IGEs vary with the extent of local heterogeneity in parental skills vs. earnings instability.

This paper develops and estimates a dynamic model of individuals’ and couples’ labor supply, savings, and retirement decisions to analyze how the design of Chile’s privatized pension system and a reform undertaken in 2008 affect gender pension gaps and old-age poverty. Chile has one of the longest-running private retirements accounts systems in the world, which has served as a model for many countries. The paper estimates the dynamic model using pre-reform data and compares the model’s short-term forecasts with reduced form estimates of the reform’s causal impacts. The model provides accurate forecasts, so it is used to evaluate how actual and counterfactual changes in the pension system design affect men’s and women’s labor supply and savings decisions, pension receipts, and program costs over a longer time horizon. The results show that three design features significantly reduce gender pension gaps: expanding minimum pension benefit eligibility, providing a per-child pension bonus, and increasing women’s retirement age to be equal to men’s. Overall, the 2008 pension reform largely achieved its goals of reducing gender gaps and old age poverty, although the new system costs double that of the old system.

We analyze the impact that the option of migration might have on human capital accumulation. We show that, when the return to education for migrants is lower in the destination than in the origin, the overall incentive to accumulate human capital is reduced as restrictions on migration are relaxed. We use panel data from the Chinese Household Income Project to document that the return to education for rural individuals is lower in urban areas than in rural areas. We then use a difference-in-differences design to show that the 1983 reform that eliminated the strong restriction that existed for rural–urban migration resulted in a reduction of 0.4 years of schooling for rural people in China. Guided by these results, we estimate a life-cycle dynamic discrete choice model of education decisions and circular rural–urban migration in which individuals differ in observable characteristics and unobservable cognitive and non-cognitive skills. We validate the model by showing it is able to replicate the impact estimates from the difference-in-differences specification. Our simulations show that, while it would take a small subsidy (conditional on staying in school) to undo about 40% of the negative effects of the 1983 policy on rural education, the annual subsidy would need to be half of annual earnings to undo the effects entirely.