Exact sign test calculator
Choose a design, paste values and read the exact two-sided p-value.
Sign counts
| Category | Count | Share |
|---|---|---|
| Fill in the fields above — the result is computed on this page. | ||
How do I use this page?
- Choose a median or paired design.
- Paste values in matching order.
- Read sign counts, ties, effective n and p-value.
What this page does not do: Doubling the smaller tail is a conservative two-sided definition for a discrete distribution. The tool does not calculate a confidence interval for the median.
Further reading
Theory — what is the sign test?
The sign test uses only the direction of the difference between a pair of measurements, whether it is positive or negative, ignoring its size. Ties, meaning pairs with no difference, are dropped from the analysis. Under the baseline hypothesis each sign is assumed to have a probability of 0.5, and the p-value is computed as the exact two-sided tail of the binomial distribution. Unlike the Wilcoxon test, the sign test does not use ranks of the magnitude of differences or assume their symmetry.
Frequently asked questions
How does it differ from Wilcoxon?
What happens to ties?
See also
A/B test calculator
Compare two proportions in an A/B test. Calculate conversion rates, difference, uplift, z score, p value and c
A/B test planning — sample size, MDE and duration
Plan a two-proportion experiment, estimate detectable effect and traffic duration.
ACF and PACF autocorrelation calculator
Calculate ACF and PACF across time-series lags. Review the chart, reference bounds and coefficient table.