Critical Value Calculator
Pick the distribution, the significance level and the tails to get the critical…
Pick the distribution, the significance level and the tails to get the critical value, with the rejection region shaded where a test would reject.
ExampleCritical t, α = 0.05
±2.2281
Reject the null hypothesis when |t| > 2.2281: the two shaded tails hold 0.025 each.
Pick your own level, or drag the cut-off.
Drag the cut-off; the shaded area is α.
- Confidence level
- 95%
- Distribution
- t (10 df)
- Tails
- Two
How this works: 10 sources,
How this works
Method
A critical value marks the edge of the rejection region: the most extreme stretch of the distribution, holding a share α of its area, where a test statistic would lead you to reject the null hypothesis. At α = 0.05 two-tailed, the z critical value is 1.96, because 2.5% of the normal curve lies beyond 1.96 on each side. Full method
Sources
- Wikipedia, Student’s t-distribution
- NIST/SEMATECH e-Handbook of Statistical Methods, 1.3.6.6.4 t Distribution
- NIST/SEMATECH e-Handbook of Statistical Methods, 1.3.6.6.6 Chi-Square Distribution
- NIST/SEMATECH e-Handbook of Statistical Methods
- Abramowitz and Stegun, Handbook of Mathematical Functions, chapters 6, 7 and 26 (1964)
- SciPy 1.18 scipy.stats (reference values for the tests)
- statsmodels 0.15 (reference values for the A/B test and regression intervals)
- Welch, The generalization of Student’s problem when several different population variances are involved (Biometrika) (1947)
- Fleiss, Levin and Paik, Statistical Methods for Rates and Proportions, 3rd edition (sample size for two proportions) (2003)
- Hyndman and Fan, Sample quantiles in statistical packages (The American Statistician) (1996)
How it’s tested
2 worked examples for this page are checked by automated tests before every release: given the inputs, the tool must show the expected answer.
Privacy
On your device. Nothing you enter or open leaves this browser. About privacy labels
Changes
- First published: live curves with draggable cut-offs, and tests on pasted data (t-tests, ANOVA, chi-square, Fisher’s exact, correlation, regression, A/B), checked against SciPy.
How critical values work
A critical value marks the edge of the rejection region: the most extreme stretch of the distribution, holding a share α of its area, where a test statistic would lead you to reject the null hypothesis. At α = 0.05 two-tailed, the z critical value is 1.96, because 2.5% of the normal curve lies beyond 1.96 on each side.
For a t test the critical value depends on the degrees of freedom. With 10 degrees of freedom the two-tailed 5% value is 2.228, noticeably above 1.96; with 30 it is 2.042 and with 120 it is 1.98, closing in on the normal value as the sample grows.
One-tailed tests put all of α in one tail, so the critical value is smaller: 1.645 for z at 5%. Chi-square is not symmetric and has no negative values, so its critical values are usually on the right only: with 4 degrees of freedom, 9.488 at α = 0.05.
two-tailed: ±F⁻¹(1 − α/2) · right-tailed: F⁻¹(1 − α) · left-tailed: F⁻¹(α)
- William Sealy Gosset published the t distribution in 1908 under the pen name Student, to work with small samples at the Guinness brewery. Source: Wikipedia, Student’s t-distribution.
- As the degrees of freedom grow, the t distribution approaches the standard normal distribution. Source: NIST/SEMATECH e-Handbook of Statistical Methods, 1.3.6.6.4 t Distribution.
- The chi-square distribution with k degrees of freedom is the distribution of a sum of k squared standard normal variables, and it takes only positive values. Source: NIST/SEMATECH e-Handbook of Statistical Methods, 1.3.6.6.6 Chi-Square Distribution.
Two-tailed t critical values by degrees of freedom
The t value that leaves α/2 in each tail, for α = 0.10, 0.05 and 0.01; the last row is the normal (z) limit.
| Degrees of freedom | α = 0.10 | α = 0.05 | α = 0.01 |
|---|---|---|---|
| 1 | 6.314 | 12.706 | 63.657 |
| 2 | 2.92 | 4.303 | 9.925 |
| 3 | 2.353 | 3.182 | 5.841 |
| 4 | 2.132 | 2.776 | 4.604 |
| 5 | 2.015 | 2.571 | 4.032 |
| 6 | 1.943 | 2.447 | 3.707 |
| 8 | 1.86 | 2.306 | 3.355 |
| 10 | 1.812 | 2.228 | 3.169 |
| 12 | 1.782 | 2.179 | 3.055 |
| 15 | 1.753 | 2.131 | 2.947 |
Show all 17 rowsShow fewer
| 20 | 1.725 | 2.086 | 2.845 |
| 25 | 1.708 | 2.06 | 2.787 |
| 30 | 1.697 | 2.042 | 2.75 |
| 40 | 1.684 | 2.021 | 2.704 |
| 60 | 1.671 | 2 | 2.66 |
| 120 | 1.658 | 1.98 | 2.617 |
| ∞ (z) | 1.645 | 1.96 | 2.576 |
Common questions
What is the critical value for a 95% confidence interval?
z* = 1.96 for a large sample or known σ; t* with n − 1 degrees of freedom otherwise (2.262 for a sample of 10, 2.045 for 30).
Critical value or p-value?
They give the same decision. Reject when the statistic is beyond the critical value, which is exactly when the p-value is below α. The p-value also tells you how far past the line you are.
Why is the t critical value bigger than z?
With a small sample the standard deviation is itself estimated, which adds uncertainty. The t distribution has fatter tails to allow for it, so you need a more extreme result to reject.