Policy Choice in Time Series by Empirical Welfare Maximization

• Department of Economics

In this seminar, Toru Kitagawa (Brown University) will present the paper: 'Policy Choice in Time Series by Empirical Welfare Maximization'.

This paper develops a novel method for policy choice in a dynamic setting where the available data is a multi-variate time series. Building on the statistical treatment choice framework, the authors propose Time-series Empirical Welfare Maximization (T-EWM) methods to estimate an optimal policy rule by maximising an empirical welfare criterion constructed using nonparametric potential outcome time series. They characterise conditions under which T-EWM consistently learns a policy choice that is optimal in terms of conditional welfare given the time-series history. They derive a non-asymptotic upper bound for conditional welfare regret. To illustrate the implementation and uses of T-EWM, the authors perform simulation studies and apply the method to estimate optimal restriction rules against Covid-19.

Co-authors: Weining Wang and Mengshan Xu