This content originally appeared on DEV Community and was authored by Njeri Kimaru
Parametric Tests
Assume your data follows a specific distribution — usually a normal distribution (bell-shaped curve).
Key assumptions:
The data is normally distributed
The sample size is large enough
Data is measured on interval or ratio scale
Homogeneity of variance (similar spread in groups)
Examples:
- t-test — Compare means between 2 groups
- ANOVA — Compare means across 3+ groups
- Pearson correlation — Relationship between two variables
- Linear regression — Predicting outcomes based on predictors
Non-Parametric Tests
Don’t assume any specific distribution of data. These are more flexible, especially for:
Skewed data
Ordinal data
Small sample sizes
Examples:
- Mann–Whitney U test — Non-parametric alternative to t-test
- Kruskal–Wallis test — Alternative to ANOVA
- Wilcoxon signed-rank — Paired samples (like paired t-test)
- Spearman correlation — Non-parametric correlation
- Chi-square test Categorical data (e.g., frequencies)
This content originally appeared on DEV Community and was authored by Njeri Kimaru