Statistical Test Decision Tree

An English-language decision guide for choosing the right statistical test, with R code and biomedical examples for every method

Choosing the right statistical test is the hinge between a defensible analysis and a reviewer’s rejection. This section offers three ways to reach the correct test for a given research question:

Sections

  • Foundations – measurement scales, descriptive statistics, normality checks, outlier handling, hypothesis testing basics.
  • Differences – comparing groups on means, medians, variances, or proportions.
  • Associations – quantifying how variables move together: correlation and regression families.
  • Interdependence – exploratory structure discovery: factor analysis, cluster analysis.

How to use this section

If you already know what you are comparing and how, jump to the relevant method page. If you need help deciding, use the wizard; it asks only the questions that change the recommendation. The static tree is the reference map – useful once you have worked through the wizard a few times and want a single-page overview.

Every example uses R (with tidyverse, rstatix, car, broom, gtsummary, ggstatsplot, psych, lavaan, factoextra, and cluster) and simulated biomedical data. No SPSS, no Python, no Stata.


Structure inspired by the University of Zurich Methodenberatung (methodenberatung.uzh.ch). All text, examples, R code, and reporting sentences are independently authored in English.

Sections

5 pages

Foundations

TOOL

Interactive Wizard

Answer a few questions and be routed to the appropriate test.

TOOL

Static Decision Tree

Visual Mermaid chart of the same routing logic.