Inferential Statistics

Hypothesis testing, confidence intervals, and the major parametric and non-parametric procedures for comparing groups and relationships

Inferential statistics is the bridge from data in hand to claims about the world. This area covers the philosophy of hypothesis testing, the construction and interpretation of confidence intervals, and the full catalogue of common tests used in the life sciences and clinical research.

Tutorials are grouped by the kind of research question being answered: comparing a single mean to a reference, comparing two or more groups, testing associations between categorical variables, and quantifying correlations between continuous variables. Non-parametric alternatives are treated in parallel with their parametric counterparts, and multiple testing correction is given its own dedicated thread.

What is covered

  • The logic of Null Hypothesis Significance Testing, type I/II errors, and the much-misunderstood p-value
  • Confidence intervals: construction, coverage, and why they are more informative than p-values alone
  • One-sample and paired-sample t-tests with assumption checks
  • Two-sample t-tests: Student’s, Welch’s, and when to choose which
  • One-way, two-way, repeated-measures, and mixed ANOVA with post-hoc testing
  • Chi-squared tests of independence and goodness-of-fit; Fisher’s exact test for small tables
  • Correlation coefficients: Pearson, Spearman, Kendall, and their inferential procedures
  • Non-parametric rank tests: Mann-Whitney U, Wilcoxon signed-rank, Kruskal-Wallis, Friedman
  • Permutation and bootstrap tests for when distributional assumptions are untenable
  • Multiple testing correction: Bonferroni, Holm, Benjamini-Hochberg (FDR), Benjamini-Yekutieli

Effect sizes are reported alongside p-values in every example, and guidance on effect-size interpretation is given for each design.

Tutorials

TUTORIAL

Anderson-Darling Test

A distribution goodness-of-fit test with emphasis on the tails

TUTORIAL

Bartlett’s Test

Test of equal variances across groups, most powerful under normality but very sensitive to its violation

TUTORIAL

Benjamini-Hochberg FDR

Controlling the expected proportion of false discoveries among rejected hypotheses

TUTORIAL

Benjamini-Yekutieli FDR

Dependence-robust false discovery rate control at the cost of conservatism

TUTORIAL

Bonferroni Correction

Controlling family-wise error rate by dividing alpha across m tests

TUTORIAL

Bootstrap Confidence Intervals

Percentile, basic, BCa, and studentised bootstrap CIs

TUTORIAL

Chi-Squared Goodness-of-Fit Test

Testing whether observed category frequencies match an expected distribution

TUTORIAL

Chi-Squared Test of Independence

Testing association between two categorical variables via observed vs. expected counts under independence

TUTORIAL

Cochran-Mantel-Haenszel Test

Stratified analysis of 2x2 tables across levels of a confounding variable

TUTORIAL

Effect Sizes: Overview

Why effect sizes matter and which measures apply to which tests

TUTORIAL

Equivalence Testing with TOST

Two one-sided tests for establishing practical equivalence within a margin

TUTORIAL

Fisher’s Exact Test

Exact test for 2x2 (and r x c) contingency tables, based on the hypergeometric distribution

TUTORIAL

Friedman Test

Non-parametric test for three or more paired / repeated measures

TUTORIAL

Holm’s Step-Down Correction

Sequential Bonferroni with uniformly greater power; controls FWER

TUTORIAL

Kendall’s Tau

Rank correlation based on concordant vs discordant pairs; robust to ties and small samples

TUTORIAL

Kolmogorov-Smirnov Test

CDF-based goodness-of-fit for one-sample and two-sample comparisons

TUTORIAL

Kruskal-Wallis Test

Non-parametric one-way ANOVA based on ranks across three or more groups

TUTORIAL

Levene’s Test of Variances

Robust test of variance homogeneity across groups

TUTORIAL

Mann-Whitney U Test

Non-parametric two-sample test based on ranks; alternative to the independent t-test

TUTORIAL

McNemar’s Test

Paired / matched binary data: comparing two measurements on the same units, using discordant pairs only

TUTORIAL

Mixed ANOVA

Designs combining between-subjects and within-subjects factors, with the interaction as key

TUTORIAL

Multiple Comparisons: Overview

Family-wise error vs false discovery rate and when each applies

TUTORIAL

Null and Alternative Hypotheses

Formulating H0 and H1, choosing one- vs two-sided tests, and avoiding post-hoc reformulation

TUTORIAL

One-Proportion Test

Testing whether an observed proportion differs from a pre-specified reference; exact and score-based methods

TUTORIAL

One-Sample t-Test

Testing whether a sample mean equals a pre-specified reference value

TUTORIAL

One-Sample z-Test

Comparing a sample mean to a reference when the population variance is known – rare in practice but pedagogically useful

TUTORIAL

One-Way ANOVA

Comparing means across three or more independent groups via the F-test

TUTORIAL

P-Values Explained

Definition, correct interpretation, and the most common misinterpretations of the p-value

TUTORIAL

Paired t-Test

Comparing two dependent measurements by applying a one-sample t-test to their differences

TUTORIAL

Pearson Correlation Test

Testing whether the Pearson correlation between two continuous variables is non-zero

TUTORIAL

Permutation Tests

Exact or Monte Carlo p-values via resampling under exchangeability

TUTORIAL

Post-Hoc Tests with Tukey HSD

Pairwise comparisons after ANOVA with family-wise error control

TUTORIAL

Repeated-Measures ANOVA

Within-subjects analysis of variance with sphericity checks and corrections

TUTORIAL

Shapiro-Wilk Normality Test

The most powerful commonly used test for normality in small to moderate samples

TUTORIAL

Spearman Rank Correlation Test

Non-parametric correlation test for monotonic association between two variables

TUTORIAL

The Bootstrap: Introduction

Resampling with replacement to estimate standard errors and sampling distributions

TUTORIAL

The Jackknife

Leave-one-out resampling for bias and variance estimation

TUTORIAL

The Runs Test

Testing randomness of a binary or dichotomised sequence via run lengths

TUTORIAL

The Sign Test

Testing a median or paired difference using only the direction of each observation

TUTORIAL

Two-Proportion Test

Comparing two independent proportions; z-test and chi-squared equivalence, with risk difference and relative risk

TUTORIAL

Two-Sample t-Test

Comparing means between two independent groups with Student’s and Welch’s t-tests, including assumption checks and effect sizes

TUTORIAL

Two-Way ANOVA

Two between-subjects factors: main effects and interaction

TUTORIAL

Type I and Type II Errors

Rejecting a true null (alpha) and failing to reject a false null (beta); power and the trade-off

TUTORIAL

Welch’s t-Test

Two-sample t-test that does not assume equal variances; R’s default

TUTORIAL

Wilcoxon Signed-Rank Test

Non-parametric paired-sample test based on signed ranks