Radboud University, Donders Institute for Brain, Cognition and Behaviour, Nijmegen , The Netherlands.
Cardiff University Brain Research Imaging Centre (CUBRIC), School of Psychology, Cardiff University , United Kingdom.
J Neurophysiol. 2018 Jun 1;119(6):2114-2117. doi: 10.1152/jn.00765.2017. Epub 2018 Feb 21.
Statistical power is essential for robust science and replicability, but a meta-analysis by Button et al. in 2013 diagnosed a "power failure" for neuroscience. In contrast, Nord et al. ( J Neurosci 37: 8051-8061, 2017) reanalyzed these data and suggested that some studies feature high power. We illustrate how publication and researcher bias might have inflated power estimates, and review recently introduced techniques that can improve analysis pipelines and increase power in neuroscience studies.
统计功效对于稳健的科学和可重复性至关重要，但 Button 等人在 2013 年进行的一项荟萃分析诊断出神经科学存在“功效不足”的问题。相比之下，Nord 等人（J Neurosci 37: 8051-8061, 2017）重新分析了这些数据，并提出其中一些研究具有较高的功效。我们说明了发表偏倚和研究人员偏倚如何夸大了功效估计，并回顾了最近引入的一些技术，这些技术可以改进神经科学研究中的分析流程并提高功效。
