Inferential Statistics

Overview

Inferential statistics are ways of analyzing and interpreting data. Inferential statistics consist of parametric and non-parametric tests. Parametric tests can be used when the data’s distribution is sufficiently close to a normal distribution, and if this is not the case, then non-parameteric tests must be used. Non-parametric tests can also be used upon normally-distributed data. So why bother with parametric tests at all? Parametric tests should be preferred over non-parametric tests whenever possible due to their increased statistical “power”…they are better at finding (or proving) relationships between variables.

Examples of parametric tests:

• One-way analysis of variance (ANOVA)
• Paried t-test
• Pearson coefficient of correlation

Examples of non-parametric tests:

• Wilcoxon signed-rank test
• Kruskal-Wallis test
• Spearman’s rank correlation