The Null Result Penalty

• 成果类型: Article
• 署名作者: Chopra, Felix; Haaland, Ingar; Roth, Christopher; Stegmann, Andreas
• 署名单位: University of Cologne; Centre for Economic Policy Research - UK; University of Copenhagen; Norwegian School of Economics (NHH); University of Cologne; Max Planck Society; University of Warwick
• 刊物名称: ECONOMIC JOURNAL
• ISSN/ISSBN: 0013-0133
• DOI: 10.1093/ej/uead060
• 发表日期: 2023
• 页码: 193-219
• 关键词: publication bias; TRANSPARENCY; science; reproducibility; replicability

摘要

We examine how the evaluation of research studies in economics depends on whether a study yielded a null result. Studies with null results are perceived to be less publishable, of lower quality, less important and less precisely estimated than studies with large and statistically significant results, even when holding constant all other study features, including the sample size and the precision of the estimates. The null result penalty is of similar magnitude among PhD students and journal editors. The penalty is larger when experts predict a large effect and when statistical uncertainty is communicated with p-values rather than standard errors. Our findings highlight the value of a pre-result review.