Prediction Intervals for Synthetic Control Methods

TL;DR

This paper develops a method for constructing prediction intervals in synthetic control analysis that account for multiple sources of uncertainty, providing finite-sample guarantees and practical tools for empirical research.

Contribution

It introduces a novel approach for uncertainty quantification in synthetic control methods, accommodating covariates and non-stationary data with simulation-based implementation.

Findings

Prediction intervals with finite-sample guarantees.

Method effectively accounts for multiple sources of randomness.

Software packages available for practical application.

Abstract

Uncertainty quantification is a fundamental problem in the analysis and interpretation of synthetic control (SC) methods. We develop conditional prediction intervals in the SC framework, and provide conditions under which these intervals offer finite-sample probability guarantees. Our method allows for covariate adjustment and non-stationary data. The construction begins by noting that the statistical uncertainty of the SC prediction is governed by two distinct sources of randomness: one coming from the construction of the (likely misspecified) SC weights in the pre-treatment period, and the other coming from the unobservable stochastic error in the post-treatment period when the treatment effect is analyzed. Accordingly, our proposed prediction intervals are constructed taking into account both sources of randomness. For implementation, we propose a simulation-based approach along with finite-sample-based probability bound arguments, naturally leading to principled sensitivity analysis methods. We illustrate the numerical performance of our methods using empirical applications and a small simulation study. \texttt{Python}, \texttt{R} and \texttt{Stata} software packages implementing our methodology are available.