Learning in Games and the Interpretation of Natural Experiments

• 成果类型: Article
• 署名作者: Fudenberg, Drew; Levine, David K.
• 署名单位: Massachusetts Institute of Technology (MIT); Washington University (WUSTL); Washington University (WUSTL)
• 刊物名称: AMERICAN ECONOMIC JOURNAL-MICROECONOMICS
• ISSN/ISSBN: 1945-7669
• DOI: 10.1257/mic.20200106
• 发表日期: 2022
• 页码: 353-377
• 关键词: state

摘要

We show that the treatment effect estimated by standard methods such as regression discontinuity analysis or difference-in-differences may contain a transient ???learning effect??? that is entangled with the long-term effect of the treatment. This learning effect occurs when the variable of interest is the agents???efforts, when treatment and con-trol correspond to success or failure: success or failure gives agents information about how much their effort matters, and consequently changes the amount of effort they provide after treatment. We exam-ine the impact of the learning effect and when it is likely to be sub-stantial. (JEL C13, C21, D72, D74, D83, I20)