Star Wars: The Empirics Strike Back

• 成果类型: Article
• 署名作者: Brodeur, Abel; Le, Mathias; Sangnier, Marc; Zylberberg, Yanos
• 署名单位: University of Ottawa; Paris School of Economics; Centre National de la Recherche Scientifique (CNRS); Aix-Marseille Universite; University of Bristol
• 刊物名称: AMERICAN ECONOMIC JOURNAL-APPLIED ECONOMICS
• ISSN/ISSBN: 1945-7782
• DOI: 10.1257/app.20150044
• 发表日期: 2016
• 页码: 1-32
• 关键词: publication bias; statistical life; social-sciences; file drawer; ECONOMICS; journals; false; metaanalysis; regression; facts

摘要

Using 50,000 tests published in the AER, JPE, and QJE, we identify a residual in the distribution of tests that cannot be explained solely by journals favoring rejection of the null hypothesis. We observe a two-humped camel shape with missing p-values between 0.25 and 0.10 that can be retrieved just after the 0.05 threshold and represent 10-20 percent of marginally rejected tests. Our interpretation is that researchers inflate the value of just-rejected tests by choosing significant specifications. We propose a method to measure this residual and describe how it varies by article and author characteristics.