Normality Distributions Commonly Used in Sport and Health Sciences

Abstract

This article provides a comprehensive exploration of univariate and multivariate hypothesis tests commonly employed to assess the normality of data distributions. Normality is a foundational assumption in various statistical analyses, rendering the evaluation of data distribution conformity to the normal distribution paramount. In this article, we discuss the principles behind univariate tests, such as the Kolmogorov-Smirnov test, Anderson-Darling test, and Shapiro-Wilk test, as well as multivariate tests, including the Mahalanobis distance and Mardia's multivariate skewness and kurtosis tests. The article aims to aid researchers and practitioners in selecting the most suitable tests for their specific data analysis requirements.