Long-term causal inference under persistent confounding via data combination

• Published in: Journal of the Royal Statistical Society. Series B, Statistical methodology Vol. 87; no. 2; pp. 362 - 388
• Main Authors: Imbens, Guido, Kallus, Nathan, Mao, Xiaojie, Wang, Yuhao
• Format: Journal Article
• Language: English
• Published: Oxford Oxford University Press 01.04.2025
• Subjects: Asymptotic methods; Employment; Inference; Job training; Long term; Short term; Synthetic data

We study the identification and estimation of long-term treatment effects by combining short-term experimental data and long-term observational data subject to unobserved confounding. This problem arises often when concerned with long-term treatment effects since experiments are often short-term due...