P-曲线 [P-curve]
定义: P-曲线是一种用于识别潜在发表偏倚的工具，其通过分析一系列独立研究结果中显著性p值的分布特征来实现。该技术基于对预期右偏分布偏离程度的评估，来判断发表偏倚的存在及其程度：若曲线呈现右偏态，则表明存在更多低而显著的p值，反映潜在真实效应的存在；若曲线呈现左偏态，则说明许多p值仅略低于0.05，暗示结果几乎不显著，揭示了研究证据的不足，并表明可能暗藏p值操纵等不当研究行为。在不存在真实效应（即真零假设成立）的情况下，如果p值的报告是完全无偏的，那么p曲线应该是一条平坦的水平线，代表p值的典型分布。
相关术语: File-drawer, Hypothesis, *P*\-hacking, *p*\-value, Publication bias (File Drawer Problem), Questionable Research Practices or Questionable Reporting Practices (QRPs), Selective reporting, Z-curve
参考文献:
- Bruns, S. B., & Ioannidis, J. P. (2016). P-curve and p-hacking in observational research. PLoS ONE, 11(2), e0149144. https://doi.org/10.1371/journal.pone.0149144
- Simonsohn, U., Nelson, L. D., & Simmons, J. P. (2014). P-curve: a key to the file-drawer. Journal of Experimental Psychology: General, 143(2), 534. https://doi.org/10.1037/a0030850
- Simonsohn, U., Nelson, L. D., & Simmons, J. P. (2014). P-curve and effect size: Correcting for publication bias using only significant results. Perspectives on Psychological Science, 9(6), 666–681. https://doi.org/10.1177/1745691614553988
- Simonsohn, U., Nelson, L. D., & Simmons, J. P. (2019). P-curve won’t do your laundry, but it will distinguish replicable from non-replicable findings in observational research: Comment on Bruns & Ioannidis (2016). PLoS ONE, 14(3), e0213454. https://doi.org/10.1371/journal.pone.0213454
原稿作者: Bettina M. J. Kern
审阅者: Sam Guay, Kamil Izydorczak, Charlotte R. Pennington, Robert M. Ross, Olmo van den Akker
翻译者: AI-driven translation tool "TransFlow" (developed by Jinbiao Yang and COSN OpenTransfer team)
译稿审阅者: Zixi Wang, Liangjie Chen, Ruoting Liu, Shuxian Jin