1,721,006 research outputs found
Measuring Human Capital and its Effects on Wage Growth
Full text linkEver since Mincer (1974), years of labor market experience were used to approximate individual's general human capital, while years of seniority were used to approximate job specific human capital. This specification is restrictive because it assumes that starting wages at a new job depend only on job market experience. In this article I investigate the effects of human capital on wage growth by using a more flexible specification of the wage equation, which allows for rich set of information on past employment spells to affect the starting wages. In addition, I endogenize the labor mobility decision. In order to illuminate the effects of human capital accumulation patterns on wage growth, I compare counterfactual career paths for representative individuals
Minimizing Bias in Selection on Observables Estimators When Unconfoundness Fails
Full text linkWe characterize the bias of propensity score based estimators of common average treatment effect parameters in the case of selection on unobservables. We then propose a new minimum biased estimator of the average treatment effect. We assess the finite sample performance of our estimator using simulated data, as well as a timely application examining the causal effect of the School Breakfast Program on childhood obesity. We find our new estimator to be quite advantageous in many situations, even when selection is only on observables.Treatment Effects, Propensity Score, Bias, Unconfoundedness, Selection on Unobservables
Essays in Health Economics
Full text linkThis dissertation consists of three chapters, each of which examines a different topic within the sphere the health economics.
In the first chapter, I use unique, proprietary medical practice data from 2019 to investigate the relationship between physicians, various categories of non-physician clinical staff, and other non-labor inputs in the production of patient office visits. Preliminary results suggest that, for some inputs, their marginal productivity has fallen over time. Cross-input elasticities generally match in terms of their historical classification as either compliments or substitutes, although the magnitudes of the elasticities have also fallen over time. One possible interpretation of these results is that medical practices have already adapted to changes in the economic, regulatory, and technological environment in which they practice and have achieved the easy efficiency gains that were once readily available to them.
In the second chapter, I use 17 years of hospital cost report data and a difference-in-differences identification strategy to examine the financial performance and utilization of safety-net hospitals in Massachusetts following the state’s 2006 reform. The results suggest the largest safety-net hospitals experienced a decline in patient revenue because of the reform and may have responded by transferring operations from inpatient facilities to outpatient centers as a cost-cutting maneuver. Other safety-net hospitals, however, did not experience the same decline in patient revenue. Should states need to reduce their supplemental payments to safety-net hospitals as part of national health care reform, these results suggest they should target their remaining funds to their most financially vulnerable safety-net hospitals.
The final chapter, co-authored with James Marton and Benjamin Ukert, evaluates the impact of the Affordable Care Act Medicaid expansion on health insurance coverage, access to care, and self-reported health for individuals with and without chronic conditions. Using five years of post-reform data (2014–2018) from the Behavioral Risk Factor Surveillance System and a difference-in-differences identification strategy, we find that the reform led to improvements in access to care and self-reported health for both groups. Although these improvements are mostly larger in magnitude for individuals with chronic conditions, the differences in magnitude are not statistically significant.Doctor of Philosophy (PhD)Economic
Exploring the Spatial Determinants of Children's Activities: Evidence from India
Full text linkThis paper investigates the choice of children's activities in India and provides recommendations for areas where policy intervention to promote schooling and combat child labor would be most successful. First, we recognize that child schooling and labor are not the only activities that children can engage in and include idleness as one of the choices. Second, we use a hierarchical model with spatially correlated random effects to analyze the determinants of the choice of children's activities. Lastly, we recommend that pro-schooling intervention be implemented in districts with favorable attitudes towards schooling and unfavorable attitudes towards idleness, while anti-child-labor interventions be implemented in districts where attitudes towards child labor are less favorable. We thus identify two groups of Indian districts to target appropriate government interventions
The Role of Social Norms in Child Labor and Schooling in India
Full text linkThis paper aims to summarize the unexplained propensity of children to engage in work, school, or neither. After controlling for a wide range of determinants of child labor, schooling, and idleness, we estimate a hierarchical model that allows for heteroskedastic, spatially correlated random effects. We use the posterior distribution of ranks of random effects to capture social norms toward children’s activities in each district and thus identify those Indian districts where social attitudes favor education and oppose child labor and idleness. We propose that government intervention be targeted at districts with pro-schooling, anti-child-labor, and anti-idleness social attitudes if limited government resources necessitate implementing minimal cost policies that have the greatest potential to succeed.Child Labor, Education, Spatial Dependence, Social Norms, India
Essays on Education, Health, and Misreported Program Participation
Full text linkMy dissertation examines the estimation of treatment effects in presence of plausible data quality limitations related to program participation status. In addition, my dissertation also uses a novel administrative dataset to estimate the impact of air pollution exposure, plausibly widening inequalities in testing conditions, on high-stakes exam performance in Tanzania. My dissertation aims to provide reliable estimates of the impact of the program(s) to help policymakers design cost-effective and potentially welfare-improving interventions. It also informs education and labor market policy on inequalities in high-stakes exam testing conditions due to air pollution exposure, which may add noise to this measure of student ability and lead to suboptimal education and labor market outcomes.
The first chapter proposes a method to consistently estimate the individual and joint treatment effect of overlapping (and exogenous) programs that are plausibly misreported. This chapter provides the asymptotic bias expression of the ordinary least squares (OLS) estimator and shows that it is not possible to determine the direction of the bias a priori. The joint treatment effect may also have an opposite sign to the true effect, which may have dramatic consequences if used to inform policy on whether the programs are complements or substitutes. This chapter then develops a consistent estimator of treatment effects using misclassification probabilities, which may be available through validation studies and other external sources. When misclassification probabilities are unknown, the chapter provides a two-step approach, estimating them in the first step and applying them in the proposed method in the second step. In addition, we present a way to compute the average marginal effects of participating in a single program in this framework with measurement error in multiple binary regressors. Monte Carlo simulations show that the estimator performs well in finite samples and is superior to the naive OLS estimator. Finally, we provide an empirical example, estimating the effect of the Supplemental Nutrition Assistance Program (SNAP) and the Special Supplemental Nutrition Program for Women, Infants, and Children (WIC) on food security and healthy eating using National Household Food Acquisition and Purchase Survey (FoodAPS) data.
The second chapter proposes a method to estimate treatment effects when program participation is plausibly missing. The chapter considers endogenous participation and explores different missing data mechanisms, including missing at random (MAR) and the general case of missing not at random (MNAR). The asymptotic bias expression for complete-case analysis OLS and Instrumental Variables (IV) estimators are provided and discussed. The chapter then proposes a consistent estimator of the treatment effects, the three-step estimator. The first step reframes the missing problem to that of misreporting by assigning missing data to program non-participation status. The second step estimates the true participation status when information regarding participation and missingness is available. The last step uses the predicted participation status to obtain consistent treatment effect estimates. Next, the chapter assesses the performance of this estimator in finite samples through Monte Carlo simulations and compares it with other approaches. An empirical example, estimating the impact of maternal prenatal smoking on birth weight using U.S. Natality data, is provided to illustrate the application of the proposed method in empirical studies.
The third chapter uses novel data on students' performance on national exams administered during secondary schooling in Tanzania to study how air pollution exposure on the day of the exam affects students' performance on these exams. The chapter leverages plausibly exogenous changes in local wind direction in an IV setup to obtain causal effects. IV estimates show that an increase in PM2.5 concentration by 10 µg/m³ on the day a student appears for the exam worsens their performance on the exam by 0.05 standard deviations. These results are robust to a host of falsification checks. The chapter also documents that the effects are pronounced for younger students, girls, students appearing for exams in government-owned examination centers, students in poorer regions, and those at the lower end of the achievement distribution. Further, the chapter provides suggestive evidence that adverse effects of air pollution on exams that test fluid intelligence drive the main results.Ph
Essays on Women\u27s Employment and Children\u27s Well-Being
Full text linkThis dissertation explores issues on women’s employment and children’s health in economics.
In chapter I, I investigate the causal effects of maternal employment on childhood obesity. Empirical analysis of the effects of maternal employment on childhood obesity is complicated by the endogeneity of mother’s labor supply. A mother’s decision to work likely reflects underlying factors – such as ability and motivation – that could directly influence child health outcomes. To address this concern, this study implements an instrumental variables (IV) strategy which utilizes exogenous variation in maternal employment coming from the youngest sibling’s school eligibility. With data on children ages 7-17 from the 1979 cohort of the National Longitudinal Survey of Youth linked to the Child Supplement, I explore the effects of maternal employment on children’s BMI z-score and probabilities of being overweight and obese. OLS estimates indicate a moderate association, consistent with the prior literature. However, the IV estimates show that an increase in mothers’ labor supply leads to large weight gains among children, suggesting that not addressing the endogeneity of maternal employment leads to underestimated causal effects.
Chapter II examines the effects of Walmart Supercenters on household and child food insecurity. Walmart Supercenters may reduce food insecurity by lowering food prices and expanding food availability. Our food insecurity-related outcomes come from the 2001-2007 waves of the December Current Population Survey Food Security Supplement. We match these data to our hand-collected data of Walmart Supercenters at the census tract-level. First, we estimate a naïve linear probability model and find that households and children who live near Walmart Supercenters are more likely than others to be food insecure. Since the location of Walmart Supercenters might be endogenous, we then turn to instrumental variables models that utilize the predictable geographic expansion patterns of Walmart Supercenters outward from Walmart’s corporate headquarters. The IV estimates suggest that the causal effect of Walmart Supercenters is to reduce food insecurity among households and children. The effect is largest among low-income families.
In the third paper, I investigate the effects of the Family and Medical Leave Act (FMLA) on women’s labor market outcomes. The FMLA is a federal policy that aims to help workers balance job and family responsibilities. However, it may have unintended consequences on employment because it imposes costs on firms. In this study, I investigate the impact of the FMLA with labor market flows—i.e., hires, separations and recalls. Focusing on labor market flow outcomes is crucial to identifying the immediate impact of the policy because employment and wages adjust slowly when there is a policy change while labor market flows are flexible. Using data from the Quarterly Workforce Indicators and adopting a triple-difference model, I get results that are unlikely to be interpreted as causal because the data are insufficient to obtain precise estimates. However, the idea of using labor market flows can be easily applied to a broad range of topics relate to workplace mandates
Essays on the Economics of Risky Health Behaviors
Full text linkThis dissertation consists of three essays studying the economics of risky health behaviors. Essay 1 estimates the effects of Graduated Driver Licensing (GDL) restrictions on weight status among adolescents aged 14 to 17 in the U.S. The findings suggest that a night curfew significantly raises adolescents’ probability of being “overweight or obese” by 1.32 percentage points, corresponding to an increase in “overweight or obesity” rate of 4.8%. A night curfew combined with a passenger restriction increases this rate by 5.8%. Overall, I estimate that nearly 16% of the rise in “overweight or obesity” rate among teenagers aged 14 to 17 in the U.S from 1999 to 2015 can be explained by the presence of the GDL restrictions. In addition, the restrictions reduce teenagers’ exercise frequency while increasing their time spent watching TV, which may help to explain the adverse effects on obesity.
Essay 2 exploits the effects of the Graduated Driver Licensing (GDL) restrictions on youth smoking and drinking. It finds that being subject to minimum entry age, a learner stage, or only a night curfew has no statistically significant effect whereas, interestingly, a night curfew combined with a passenger restriction reduces youth smoking and drinking. The estimated effects become more statistically significant and larger in magnitude in the medium run, which is in line with the addictive nature of these substances.
Essay 3 investigates the underlying causes of suicide. It uses data from the U.S. at the county level and the primary methodology is a two-level Bayesian hierarchical model with spatially correlated random effects. The results show that the significant effects of observable factors on suicides found by earlier research may partially stem from excluding small area effects and time trends, without controlling for which the true contribution of unobserved propensities and time trends can be hidden within observable factors. Most importantly, a lot can be learned from unobserved yet persistent propensity toward suicide captured by the spatially correlated county specific random effects. Resources should be allocated to counties with high suicide rates, but also counties with low raw suicide rates but high unobserved propensities of suicide
On the Specification of Propensity Scores: with Applications to the Analysis of Trade Policies
Full text linkThe use of propensity score models for program evaluation with non-experimental data typically requires the propensity score be estimated, often with a model whose specification is unknown. While theoretical results suggest that estimators utilizing more flexible propensity score specifications perform better, this has not filtered into applied research. Here, we provide Monte Carlo evidence indicating benefits of over-specifying the propensity score that are robust across a number of different covariate structures and estimators. We illustrate these results with two applications, one assessing the environmental effects of GATT/WTO membership and the other assessing the impact of euro adoption on bilateral trade.Treatment Effects, Program Evaluation, WTO, Environment, Currency Union
- …
