The normal distribution is not normal in psychological data: Moving beyond parametric dogma

心理学数据并非总是服从正态分布:超越参数教条

阅读:1

Abstract

Psychological research has traditionally relied on parametric statistical methods, largely due to the historical convenience of the normal distribution. However, empirical evidence shows that psychological and mental health data often violate normality assumptions, exhibiting skewness, kurtosis, ordinal scaling, and outliers. Common constructs such as stress, anxiety, and substance use frequently display zero-inflated or asymmetric distributions, making parametric methods inappropriate and potentially misleading. Violations of normality increase the risk of Type I and II errors, bias effect estimates, and undermine inferential validity. While non-parametric tests offer more robust alternatives, modern resampling techniques such as bootstrapping and Monte Carlo simulations provide greater flexibility and accuracy without relying on strict distributional assumptions. This paper illustrates common deviations from normality in psychological data and advocates for a paradigm shift toward assumption-light analytical strategies. Emphasizing data visualization, transparent reporting, and statistical education, we argue for broader adoption of flexible methods to ensure more valid, interpretable, and reproducible findings in psychological science.

特别声明

1、本页面内容包含部分的内容是基于公开信息的合理引用;引用内容仅为补充信息,不代表本站立场。

2、若认为本页面引用内容涉及侵权,请及时与本站联系,我们将第一时间处理。

3、其他媒体/个人如需使用本页面原创内容,需注明“来源:[生知库]”并获得授权;使用引用内容的,需自行联系原作者获得许可。

4、投稿及合作请联系:info@biocloudy.com。