Parametric Versus Non-Parametric Statistics: A Case Study in Traditional and Alternative Medicine Research with the Development of SDA4AMR Web Application

Abstract

This study investigated the performance of parametric and non-parametric tests, specifically, the one-sample t-test and the Wilcoxon Signed-Rank (WSR) test, through simulation-based evaluations of type I error rates and statistical power across varying sample sizes and effect sizes. Complementing the simulation study, we conducted a systematic review of empirical articles published in two journals in traditional and alternative medicine to assess the usage of statistical methods and the reporting of assumption checks. Simulation results revealed that the t-test generally maintained acceptable type I error rates under Bradley’s criterion, especially when sample sizes were 20 or greater. In contrast, the WSR test frequently exhibited inflated error rates, particularly with larger samples. In terms of power, the t-test consistently outperformed the WSR test, though both achieved satisfactory power (≥ 0.8) under appropriate conditions. These findings underscore the importance of context-specific test selection, striking a balance between robustness and statistical sensitivity. Furthermore, the journal review revealed that, although a majority of articles employed inferential statistics, assumption checking was rarely reported, even for commonly used methods such as t-tests, ANOVA, and chi-square tests. This lack of transparency raises concerns about the validity of statistical conclusions drawn in the literature. Therefore, to support better statistical practice, the Smart Data Analysis Web Application for Alternative Medicine Research (SDA4AMR) was developed. This tool facilitates the selection of appropriate tests, automatic assumption checking, and interpretable outputs. By enhancing accessibility and encouraging methodological rigor, SDA4AMR aims to improve research quality and reproducibility in the field of traditional and alternative medicine.