Tests for Comparison of Two Groups: Student’s T-test, Mann-Whitney U-test and Chi-square Test

Abstract

Background. Determining the significance of the difference between two study groups is performed using statistical tests, the choice of which depends on the character and distribution of data in those groups. Objective. The aim of this manuscript is to explain the logic and conditions of application of statistical tests for the comparison of two study groups. Methods. The manuscript was prepared as a narrative review article, based on the primary statistical literature. Results. The Student’s T-test and the Mann-Whitney U-test can be applied to the comparison of the values of a continuous variable between two groups, with the Student’s T-test subject to the mandatory condition that the data are normally distributed in both groups (the normality of the distribution is checked by Kolmogorov-Smirnov test). The Chi-square test is applied if the values of a categorical variable are compared between two groups, provided that none of the values is represented in less than 6 patients. Conclusions. A prerequisite for accurately determining the significance of the difference between two groups is the application of an appropriate statistical test for which all conditions are met.