Efficient Difference-in-Differences Estimation with High-Dimensional Common Trend Confounding

• Tác giả: Michael Zimmert
• Ngôn ngữ: eng
• Ký hiệu phân loại: 001.434 Experimental method
• Thông tin xuất bản: 2018
• Bộ sưu tập: Báo, Tạp chí
• ID: 162197

Tóm tắt

This study considers various semiparametric difference-in-differences models under different assumptions on the relation between the treatment group identifier, time and covariates for cross-sectional and panel data. The variance lower bound is shown to be sensitive to the model assumptions imposed implying a robustness-efficiency trade-off. The obtained efficient influence functions lead to estimators that are rate double robust and have desirable asymptotic properties under weak first stage convergence conditions. This enables to use sophisticated machine-learning algorithms that can cope with settings where common trend confounding is high-dimensional. The usefulness of the proposed estimators is assessed in an empirical example. It is shown that the efficiency-robustness trade-offs and the choice of first stage predictors can lead to divergent empirical results in practice.