The rank tests and outlier checks
toolbox.
Compare paired or grouped data without assuming normality, then check a sample for one extreme value.
Keep this toolbox for offline use
12 useful places to start.
Rank tests lose some power when the data really are normal and need independent observations. An outlier test flags a value for a closer look; it never licenses deleting data.
Wilcoxon signed-rank test calculator
Test paired measurements, or one sample against a value, with the Wilcoxon signed-rank test: V, an exact or normal p-value, a rank-biserial effect size and a pseudo-median interval.
Mann–Whitney U test calculator
Compare two independent groups without assuming a normal distribution, with exact p-values for small samples.
Kruskal-Wallis test calculator with Dunn post-hoc comparisons
Compare three or more groups without assuming normality using the Kruskal-Wallis test: tie-corrected H, p-value, epsilon-squared effect size and Dunn pairwise comparisons.
Grubbs outlier test calculator
Check one list of numbers for a single outlier with Grubbs’ test: the G statistic, critical value, p-value, the flagged value and its position, two-sided or one-sided.
Interquartile outlier finder
List values outside configurable interquartile-range fences.
One-way ANOVA calculator
Compare the means of two or more groups with an F test and an ANOVA table.
Welch two-sample t test
Compare independent sample means without assuming equal variances.
Spearman rank correlation
Measure the association between two paired lists using ranks.
Normal Q-Q plot and normality tests
Draw a normal Q-Q plot of your numbers and check them with the Jarque-Bera, D’Agostino-Pearson and Anderson-Darling tests.
Box plot builder
Compare grouped distributions, medians, spread and outliers from your own CSV.
Multiple comparisons p-value correction
Adjust several p-values with Bonferroni, Holm or Benjamini–Hochberg corrections.
Descriptive statistics
Mean, median, mode, spread and standard deviation for your numbers.
A few things you
can tick off.
- Test paired measurements without assuming normality
- Compare three or more groups by ranks
- Check one extreme value with Grubbs’ test
- Look at a distribution before choosing a test