Statistics

Mann–Whitney U Test Calculator (Wilcoxon Rank-Sum) with Exact p-Value

Compare two independent groups when the data are skewed, ordinal (like Likert scores) or have outliers. Paste the two groups and get U, the exact or normal-approximation p-value with tie correction, the effect size r, the Hodges–Lehmann shift with its confidence interval, a box plot and a sentence for your results section.

✅ No login needed100% freeRuns in your browserYour data stays on your device
Mann-Whitney U Test Calculator✅ Free · no login📚 Cite this tool
Your data never leaves your PC. Your data is analysed on your own computer or phone, even when you upload a CSV or Excel file. Nothing is uploaded, stored or seen by Codanics, and no login is needed.

Separate values with spaces, commas or new lines. The groups can have different sizes.

  • PriceFree, no login or sign-up needed
  • Your dataProcessed in your browser, never uploaded
  • Works onPhone, tablet or computer, any modern browser
  • Made byDr. Muhammad Aammar Tufail, Codanics
  • Published16 November 2026
  • Last updated16 November 2026

📚 How to cite this tool

This tool is free. If it helped your thesis, paper, report or assignment, please cite it. It keeps the tools free and helps other students find them.

Citation · APA 7th edition

Tufail, M. A. (2026). Mann–Whitney U test calculator [Online tool]. Codanics. Retrieved 16 November 2026, from https://codanics.com/tools/mann-whitney-u-test-calculator/

In-text citation: (Tufail, 2026) · Narrative: Tufail (2026)

The access date is today’s date, filled in automatically. Author: Muhammad Aammar Tufail. Published 16 November 2026.

🚀 Follow Codanics channel on WhatsApp for more updatesNew free tools, scholarships, PhD positions and research tips, straight to your phone. Free lessons on YouTube too.

How to use the Mann-Whitney U Test Calculator

  1. Type or paste the values of each group into its box, or use Paste from Excel or Upload CSV / Excel. A long-format sheet (a group column and a value column) is split into the two groups for you. Rename the groups so the results read naturally.
  2. Keep the two-tailed test unless you decided on a direction before collecting the data. Leave the p-value method on Automatic: it uses the exact distribution for groups under 50 values (as R does) and the tie-corrected normal approximation for larger samples.
  3. Click Run Mann–Whitney test. Read U, the p-value and the effect size r, and check the box plot.
  4. Copy the APA sentence into your results section and download the box plot for your thesis or paper.

When should I use the Mann–Whitney U test?

The Mann–Whitney U test (also called the Wilcoxon rank-sum test) compares two independent groups. It works on the ranks of the data instead of the raw values, so it does not need normally distributed data. Use it instead of the independent-samples t-test when:

  • the outcome is ordinal, for example Likert scores, pain ratings or disease scores;
  • the data are clearly skewed or have outliers, and the samples are small;
  • a normality test or a Q–Q plot shows a strong departure from normality.
Your designParametric testNon-parametric test
Two independent groupsIndependent t-test (Welch)Mann–Whitney U
Same subjects measured twicePaired t-testWilcoxon signed-rank
Three or more independent groupsOne-way ANOVAKruskal–Wallis

Not sure? The which statistical test should I use wizard walks you through the choice.

How the test works

Rank all N = n₁ + n₂ values together (ties get the average rank). U₁ = R₁ − n₁(n₁ + 1)/2 R₁ = sum of the ranks in group 1 U₂ = n₁n₂ − U₁ reported U = min(U₁, U₂) z = (U₁ − n₁n₂/2 − c) / σ_U c = 0.5 continuity correction (optional) σ_U = √[ n₁n₂/12 · ( (N + 1) − Σ(t³ − t) / (N(N − 1)) ) ] t = size of each tie group r = |z| / √N (z without continuity correction) Hodges–Lehmann shift = median of all n₁ × n₂ differences (x − y)

When both groups have fewer than 50 values, the tool uses the exact distribution of U, as R does by default. With tied values, the exact distribution is computed given the tied ranks (the method used by R 4.4 and later). For larger samples it uses the tie-corrected normal approximation. All results, including the Hodges–Lehmann confidence interval, match R’s wilcox.test(x, y, conf.int = TRUE).

Assumptions

  • The two groups are independent, and observations within each group are independent.
  • The outcome is at least ordinal (values can be ranked).
  • To interpret the result as a difference in medians, the two distributions should have a similar shape. If the shapes differ, interpret it as “values in one group tend to be higher” (stochastic dominance).

How to report a Mann–Whitney U test (APA)

Report the medians of both groups, U, z (for the normal approximation), the p-value and an effect size, for example:

A Mann–Whitney U test showed that the treatment group (Mdn = 8.30) had significantly higher values than the control group (Mdn = 6.20), U = 7, p < .001, r = .73.

As a rule of thumb, r = .10 is a small, .30 a medium and .50 a large effect. Need to learn the basics first? Read the free ABC of statistics series, or learn to run the test yourself in the R with Aammar course.

Learn the statistics behind these numbers. Codanics has free statistics, R and Python lessons on YouTube and full courses for researchers.

Frequently asked questions

Is the Mann–Whitney U test the same as the Wilcoxon rank-sum test?

Yes. They are two versions of the same test and give the same p-value. Mann and Whitney’s U and Wilcoxon’s rank sum W differ only by a constant: U₁ = W₁ − n₁(n₁ + 1)/2. R’s wilcox.test reports this U₁ and calls it W.

Does the Mann–Whitney test compare medians?

Only if both groups have distributions of the same shape. In general it tests whether values in one group tend to be larger than in the other. That is why this tool also reports the Hodges–Lehmann shift and the probability of superiority, which describe that difference directly.

When is the exact p-value used?

With the automatic setting, the exact p-value is used when both groups have fewer than 50 values, exactly as in R 4.4 and later. If there are tied values, the exact distribution is computed conditionally on the tied ranks, which is also what R does. For larger samples, the tool uses the normal approximation with tie correction and, if ticked, the continuity correction. Older software (SPSS, older R versions) uses the normal approximation whenever there are ties; choose Normal approximation to reproduce those results.

Which U should I report, the smaller or the larger?

Most textbooks and SPSS report the smaller of U₁ and U₂, which is what the tool shows as U. Both values are listed under Test details, so you can report either and say which group it refers to.

How do I calculate the effect size for a Mann–Whitney test?

Use r = |z| / √N, where N is the total sample size. Values around .10, .30 and .50 are small, medium and large. The rank-biserial correlation, also shown, is another popular effect size and ranges from −1 to 1.

Can I use the Mann–Whitney test for Likert-scale data?

Yes, it is one of the most common choices for comparing two groups on a single Likert item or other ordinal ratings. Expect many ties; the tool corrects for them automatically.

Is my data uploaded?

No. The test runs entirely in your browser. Pasted and uploaded data never leave your device.

Do I need to log in or create an account to use the Mann-Whitney U Test Calculator?

No. There is no login, no sign-up and no email required. Open the page and start using it straight away, for free, on any device.

How do I cite this tool in my thesis or paper?

Use the citation box on this page. In APA 7th edition: Tufail, M. A. (2026). Mann–Whitney U test calculator [Online tool]. Codanics. Retrieved [date you used it], from https://codanics.com/tools/mann-whitney-u-test-calculator/. BibTeX, RIS (EndNote, Mendeley, Zotero), MLA, Harvard, Chicago and Vancouver formats are also available.

Free guides and courses from Codanics

More free tools

See all free Codanics tools → · Codanics on YouTube · WhatsApp channel

Made by Dr. Muhammad Aammar Tufail, Codanics. First published 16 November 2026, last updated 16 November 2026. Found a bug or have an idea for a new tool? Tell us on the WhatsApp channel or in the comments on YouTube. Results are for learning and planning; check important analyses with a statistician or your supervisor.