Bonferroni Correction Calculator
Test cases replayed : 3 of 3 match · Methodology · No outside source listed
Enter your overall significance level, the number of tests and, optionally, one test's p-value.
Result
Bonferroni-corrected α (α ÷ m)
Šidák-corrected α (1 − (1 − α)^(1/m))
- Bonferroni-adjusted p-value (min(1, p × m))
- This test
Estimate for planning only, not tax, legal, financial or medical advice. This calculator uses the method explained on this page.
This browser did not allow copying. The sentence is in the box below, already selected: copy it with your keyboard or the menu.
How to use this calculator
Fill in the fields in this order; each step takes you to its field.
- Overall significance level α: enter a number from 0 to 1.
- Number of tests (m): enter 1 or more.
- p-value of one test: enter a number from 0 to 1.
- Read the result: Bonferroni-corrected α (α ÷ m); the panel also shows Šidák-corrected α (1 − (1 − α)^(1/m)), Bonferroni-adjusted p-value (min(1, p × m)) and This test.
How this calculator works
Bonferroni: test each of the m hypotheses at α ÷ m, which keeps the probability of at least one false positive (the family-wise error rate) at or below α. Equivalently, multiply each p-value by m (capped at 1) and compare it with α.
Šidák's level 1 − (1 − α)^(1/m) is exact for independent tests and slightly less strict than Bonferroni.
The formula
| Symbol | Meaning | Unit |
|---|---|---|
| Overall significance level α | ||
| Number of tests | m | |
| Bonferroni-corrected α (α ÷ m) |
Worked example
| Overall significance level α | 0.05 |
|---|---|
| Number of tests (m) | 10 |
| p-value of one test | 0.004 |
| Šidák-corrected α (1 − (1 − α)^(1/m)) | 0.0051 |
|---|---|
| Bonferroni-adjusted p-value (min(1, p × m)) | 0.04 |
| This test | Significant after correction |
Bonferroni-corrected α (α ÷ m) 0.005
Each step uses the unrounded value of the step before it; figures on this page are rounded for display.
Frequently asked questions
What is the Bonferroni α for 10 tests at 0.05?
0.05 ÷ 10 = 0.005. A test with p = 0.004 stays significant.
Is the Bonferroni correction too strict?
With many tests it can be conservative and miss real effects; step-down methods such as Holm's keep the same error control with more power.