How Credible Is the Credibility Revolution?
通过模型分析经济学顶级期刊中t统计量的分布，发现65%的窄拒绝和41%的所有拒绝（|t|<10）可能是错误拒绝，质疑了实证研究的可信度。
Economists analyzing a well-conducted randomized controlled trial or natural experiment and finding a statistically significant effect conclude that the null of no effect is unlikely to be true. But how frequently is this conclusion warranted? The answer depends on the proportion of tested nulls that are true and the test's power. I model the distribution of t-statistics in leading economics journals. Using my preferred model, 65% of narrowly rejected null hypotheses and 41% of all rejected null hypotheses with |t|<10 are likely to be false rejections. For the null to have only a .05 probability of being true requires a t of 5.48.