Wilcox Rand R, Serang Sarfaraz
University of Southern California, Los Angeles, CA, USA.
Educ Psychol Meas. 2017 Aug;77(4):673-689. doi: 10.1177/0013164416667983. Epub 2016 Oct 6.
The article provides perspectives on values, null hypothesis testing, and alternative techniques in light of modern robust statistical methods. Null hypothesis testing and values can provide useful information provided they are interpreted in a sound manner, which includes taking into account insights and advances that have occurred during the past 50 years. There are, of course, limitations to what null hypothesis testing and values reveal about data. But modern advances make it clear that there are serious limitations and concerns associated with conventional confidence intervals, standard Bayesian methods, and commonly used measures of effect size. Many of these concerns can be addressed using modern robust methods.
本文依据现代稳健统计方法，对价值观、零假设检验及替代技术进行了探讨。零假设检验和p值若能以合理方式进行解读，包括考虑过去50年中出现的见解和进展，便可提供有用信息。当然，零假设检验和p值在揭示数据方面存在局限性。但现代进展表明，传统置信区间、标准贝叶斯方法及常用效应量测量方法也存在严重局限性和问题。其中许多问题可通过现代稳健方法加以解决。
