Fidler Fiona, Thomason Neil, Cumming Geoff, Finch Sue, Leeman Joanna
La Trobe University, Melbourne, Australia.
Psychol Sci. 2004 Feb;15(2):119-26. doi: 10.1111/j.0963-7214.2004.01502008.x.
Since the mid-1980s, confidence intervals (CIs) have been standard in medical journals. We sought lessons for psychology from medicine's experience with statistical reform by investigating two attempts by Kenneth Rothman to change statistical practices. We examined 594 American Journal of Public Health (AJPH) articles published between 1982 and 2000 and 110 Epidemiology articles published in 1990 and 2000. Rothman's editorial instruction to report CIs and not p values was largely effective: In AJPH, sole reliance on p values dropped from 63% to 5%, and CI reporting rose from 10% to 54%; Epidemiology showed even stronger compliance. However, compliance was superficial: Very few authors referred to CIs when discussing results. The results of our survey support what other research has indicated: Editorial policy alone is not a sufficient mechanism for statistical reform. Achieving substantial, desirable change will require further guidance regarding use and interpretation of CIs and appropriate effect size measures. Necessary steps will include studying researchers' understanding of CIs, improving education, and developing empirically justified recommendations for improved statistical practice.
自20世纪80年代中期以来，置信区间（CI）在医学期刊中已成为标准。我们通过调查肯尼斯·罗斯曼为改变统计实践所做的两次尝试，从医学的统计改革经验中探寻心理学可借鉴的经验教训。我们查阅了1982年至2000年间发表在《美国公共卫生杂志》（AJPH）上的594篇文章，以及1990年和2000年发表在《流行病学》上的110篇文章。罗斯曼关于报告置信区间而非p值的编辑指令在很大程度上是有效的：在《美国公共卫生杂志》上，仅依赖p值的情况从63%降至5%，而报告置信区间的情况从10%升至54%；《流行病学》的情况显示出更强的依从性。然而，这种依从性只是表面的：很少有作者在讨论结果时提及置信区间。我们的调查结果支持了其他研究表明的观点：仅靠编辑政策不足以实现统计改革。要实现实质性的、理想的变革，将需要关于置信区间的使用和解释以及适当效应量测量的进一步指导。必要的步骤将包括研究研究人员对置信区间的理解、改进教育，并为改进统计实践制定基于实证的合理建议。
