← Math & statistics

StatisticsPaired nonparametric

Wilcoxon Signed-Rank Test Calculator

Other languages 日本語 | English

Use Wilcoxon signed-rank when paired before/after data matter but a paired t-test feels too distribution-heavy. This page keeps the focus on ranked paired differences, the selected p-value, and whether the result is exact or approximate.

How to use

  1. Paste paired before and after values in the same row order.
  2. Choose whether the directional question is after > before, after < before, or two-sided.
  3. Read the p-value together with the number of non-zero pairs and whether the page used an exact or approximate path.

Wave 35 paired nonparametric entry

Read a paired rank-sum shift

The share URL stores only the selected tail and decimal places.

Enter paired before/after values to review the Wilcoxon signed-rank exact or asymptotic p-value.

How to choose between nearby pages

Use paired t-test when paired differences are comfortable under a mean-based normal approximation. Use McNemar test when the paired outcome is binary in a 2x2 table. Use this page when paired data are ordinal or skewed and the next question is a signed-rank p-value rather than a mean difference.

FAQ

What does this page calculate?

It runs a Wilcoxon signed-rank test on paired before/after values and reports the selected p-value, rank sums, and an exact or asymptotic read depending on the data shape.

When should I use Wilcoxon signed-rank instead of a paired t-test?

Use Wilcoxon signed-rank when the data are paired but the differences are skewed, ordinal, or too non-normal for a comfortable paired t-test interpretation.

Why is the page using a normal approximation?

If absolute differences tie, the exact signed-rank distribution is not used here. The page switches to a normal approximation and warns you when that happens.

Does the share URL include my paired values?

No. The share URL stores only light settings such as the alternative and decimal places. Your paired values stay in your browser.