The Quant's Detective Kit

A complete guide to statistical tests for hypothesis testing.

Parametric Tests

The Professional Chef: Assumes data meets certain standards (e.g., normal distribution). Precise and powerful when assumptions are met.

T-Test

Compares the means of two groups, assuming normal distribution.

Z-Test

Compares means of large samples (n>30) with known population variance.

ANOVA

Compares the averages of three or more groups.

F-Test

Compares the variances (spread) of two or more groups.

Pearson Correlation

Measures the linear relationship between two continuous variables.

Non-Parametric Tests

The Campfire Cook: Makes no strict assumptions. More flexible and robust, especially with unusual, ranked, or non-normal data.

Chi-Squared Test

Analyzes categorical data to find significant relationships.

Mann-Whitney U Test

Alternative to the T-Test when data is not normally distributed.

Kruskal-Wallis Test

Alternative to ANOVA for comparing three or more groups.

Wilcoxon Signed-Rank Test

Alternative to the paired T-Test for repeated measurements.

Spearman's Rank Correlation

Measures the monotonic relationship between two ranked variables.

Friedman Test

The non-parametric alternative to a repeated-measures ANOVA.

Kolmogorov-Smirnov (K-S) Test

Tests if a sample is drawn from a specific distribution.