Algorithm is Experiment: Machine Learning, Market Design, and Public Policy Eligibility Rules
POSITION FILLED
FACULTY SUPERVISOR:
Yusuke Narita
PROJECT DESCRIPTION:
Machine learning, market design, and other algorithms produce a growing portion of decisions and recommendations both in policy and business. Such algorithmic decisions are natural experiments (conditionally quasi-randomly assigned instruments) since the algorithms make decisions based only on observable input variables. We use this observation to develop a treatment-effect estimator for a class of stochastic and deterministic decision-making algorithms. Our estimator is shown to be consistent and asymptotically normal for well-defined causal effects. A key special case of our estimator is a multidimensional regression discontinuity design. We apply our estimator to a variety of policy and business problems. For example, we evaluate the effect of the Coronavirus Aid, Relief, and Economic Security (CARES) Act, where hundreds of billions of dollars worth of relief funding is allocated to hospitals via an algorithmic rule. Our estimates suggest that the relief funding has little effect on COVID-19-related hospital activity levels. Naive OLS and IV estimates exhibit substantial selection bias.
We look for a pre-doc fellow who will assist empirical work. The predoc fellow may also work on other empirical projects on applied microeconomics and policy analysis. The work is often joint with other researchers, so the fellow will have opportunities to work with other other faculty members at Yale and other schools.
REQUISITE SKILLS AND QUALIFICATIONS:
This project involves econometric/statistical and empirical aspects. An ideal candidate is someone who has done coursework in econometrics, machine learning, and empirical microeconomics such as labor economics and economic of education.