Abstract: This chapter illustrates flow chart to determine the most appropriate statistical test. This chart shows different kinds of data. To test for the difference between variables, various statistical tests are used. These are unpaired t-test, paired t-test, Mann-Whitney U test, Pearson's chi-square test, Wilcoxon signed-rank test, Kruskal-Wallis test, one-way analysis of variance (ANOVA), two-way ANOVA, and ANOVA repeated measures. To test for the relationship between variables, the following correlation analyses are used: Pearson's correlation; Spearman's correlation; and simple linear regression. Parametric tests (like the t-test and ANOVA) compare means and associated values (e.g., standard deviations). Nonparametric tests (like the Mann-Whitney U, Wilcoxon signed-rank, and Kruskal-Wallis tests) do not calculate parameters; therefore, they lack any assumptions about the sampling population. Nonparametric tests are also known as distribution-free applications because the data do not need to follow a normal distribution.
Publication Year: 2017
Publication Date: 2017-07-28
Language: en
Type: other
Indexed In: ['crossref']
Access and Citation
AI Researcher Chatbot
Get quick answers to your questions about the article from our AI researcher chatbot