Applied microeconomic research increasingly focuses on applications involving large numbers of unit-specific parameters. Examples include studies of school, teacher, and physician quality; neighborhood effects on economic mobility; firm effects on wages; employer-specific labor market discrimination; and individualized treatment effect predictions and policy recommendations. Empirical Bayes methods offer powerful tools for summarizing heterogeneity, estimating individual effects, and making decisions in these settings. This session will cover theory and applications of empirical Bayes methods, with an emphasis on developing skills to deploy these methods in realistic applications. Topics will include methods for quantifying variation in effects, empirical Bayes shrinkage, connections to machine learning methods, and large-scale inference tools for multiple testing and decision-making. By the end of the course, participants will be equipped to utilize these methods in their own research or business applications
- Lecture: Empirical Bayes framework and recipe, linear shrinkage, James/Stein theorem
- Lecture: Combining estimators, EB and regression, EB decision rules, connections to machine learning, EB vs. full Bayes
- Coding lab 1: School value-added
- Live-coding of solutions to lab 1
- Lecture: Flexible variance estimation, precision-dependence, deconvolution, non-parametric shrinkage
- Coding lab 2: Employer-level labor market discrimination
- Live-coding of solutions to lab 2
- Lecture: Large-scale inference – EB for multiple testing
- Coding lab 3: Classifying employer-level discrimination
- Live-coding of solutions to lab 3
-
Angrist, Hull, Pathak, and Walters (2017). "Leveraging lotteries for school value-added: testing and estimation." Quarterly Journal of Economics 132(2).
-
Efron (2012). Large-scale inference: Empirical Bayes methods for estimation, testing, and prediction. Cambridge University Press.
-
Kline and Walters (2021). "Reasonable Doubt: Experimental detection of job-level employment discrimination." Econometrica 89(2).
-
Kline, Rose, and Walters (2022). “Systemic discrimination among large US employers.” Quarterly Journal of Economics 137(4).
-
Kline, Rose and Walters (2023). "A Discrimination Report Card" (working paper)
-
Koenker and Gu (2017). “REBayes: an R package for empirical Bayes mixture methods.” Journal of Statistical Software 82(1).
-
Morris (1983). “Parametric Empirical Bayes Inference: Theory and Applications.” Journal of the American Statistical Association 78(381).
-
Narasimhan, B., and Efron, B. (2020). “deconvolveR: A g-modeling program for deconvolution and empirical Bayes estimation.” Journal of Statistical Software 94(11).