ESTIMATION OF TREATMENT EFFECTS WITHOUT AN EXCLUSION RESTRICTION: WITH AN APPLICATION TO THE ANALYSIS OF THE SCHOOL BREAKFAST PROGRAM

The increase in childhood obesity has garnered the attention of many in policymaking circles. Consequently, school nutrition programs such as the School Breakfast Program (SBP) have come under scrutiny. The identification of the causal effects of such programs, however, is difficult owing to non‐random selection into the program and the lack of exclusion restrictions. Here, we propose two new estimators aimed at addressing this situation. We compare our new estimators to existing approaches using simulated data. We show that while correlations might suggest that SBP causes childhood obesity, SBP is likely to reduce childhood obesity once selection is addressed. Copyright © 2012 John Wiley & Sons, Ltd.     

Exploring the spatial determinants of children’s activities: evidence from India

This article 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 sole 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 toward schooling and unfavorable attitudes toward idleness, while anti-child-labor interventions be implemented in districts where attitudes toward child labor are less favorable. We thus identify two groups of Indian districts to target appropriate government interventions.     

Estimating the Associations between SNAP and Food Insecurity,Obesity, and Food Purchases with Imperfect Administrative Measures of Participation

Administrative data are considered the “gold standard” when measuring program participation, but little evidence exists on their potential problems or implications for econometric estimates. We explore these issues using the FoodAPS, a unique data set containing two different administrative measures of Supplemental Nutrition Assistance Program (SNAP) participation and a survey‐based measure. We document substantial ambiguity in the two administrative measures and show that they disagree with each other almost as often as they disagree with self‐reported participation. Estimated participation and misreporting rates can be meaningfully sensitive to choices made to resolve this ambiguity and disagreement. We explore sensitivity in regression estimates of the associations between SNAP and food insecurity, obesity, and the healthy eating index. The signs are unchanged across the three measures, and the estimates are mostly not statistically different from each other. However, there are some meaningful differences in the magnitudes and levels of statistical significance of the estimates.     

MEASURING HUMAN CAPITAL AND ITS EFFECTS ON WAGE GROWTH

Abstract Ever since Mincer, years of labour 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 paper, I investigate the effects of human capital on wage growth by using a more flexible specification of the wage equation, which allows for a rich set of information on past employment spells to affect the starting wages. In addition, I endogenize the labour mobility decision. In order to illuminate the effects of human capital accumulation patterns on wage growth, I compare counterfactual career paths for representative individuals.     

Estimating high-dimensional demand systems in the presence of many binding non-negativity constraints

Two econometric issues arise in the structural estimation of consumer or producer demand systems in the presence of many binding non-negativity constraints. Firstly, most existing methods entail the evaluation of multivariate probability integrals. Secondly, the issue of statistical coherency must be addressed. We circumvent both of these issues using Gibbs’ Sampling, along with data augmentation and rejection sampling. We illustrate our method using several simulated data sets.