Causal Inference with Time-Series Cross-Sectional Data

Abstract

Abstract This chapter surveys new development in causal inference using time-series cross-sectional (TSCS) data. It starts by clarifying two identification regimes for TSCS analysis: one under the strict exogeneity assumption and one under the sequential ignorability assumption. It then reviews three most commonly used methods by political scientists: the difference-in-differences approach, two-way fixed effects models, and the synthetic control method. For each method, the chapter examines its assumptions, explain its pros and cons, and discuss its extensions. It then introduces several new methods under strict exogeneity or sequential ignorability, including the factor-augmented approach, PanelMatch, and marginal structural models. It concludes by providing some recommendations to applied researchers and pointing out several directions for future research.