Statistical table
Chi-Square Table (χ² Distribution Table)
Chi-square table of right-tail critical values for df 1–100 and α from 0.995 to 0.001, with an exact lookup, p-value ranges, worked examples and a free PDF.
Updated
Quick answer
A chi-square table gives critical values of the χ² distribution: for each number of degrees of freedom, the value that has a stated area to its right. Find the df row, move to the column for your right-tail area α, and reject H₀ if your χ² statistic is larger than the value shown. For a test with df = 4 at α = 0.05, the critical value is 9.488.
Find any chi-square critical value
Shows the right-tail p-value.
Right-tail critical value χ²(0.05, 10)
18.307
What is a chi-square table?
The chi-square distribution is the distribution of a sum of squared independent standard normal variables. Its shape depends only on the degrees of freedom: it is strongly right-skewed for small df and becomes more symmetric as df grows, and its mean equals df. Chi-square statistics measure how far observed counts, or a sample variance, depart from what the null hypothesis predicts, so large values count as evidence against H₀. It is also called a chi-square distribution table, a chi-square critical value table, a χ² (X²) table or a chi-square chart, and it is the table used for every chi-square test.
This table gives right-tail critical values. Each column heading is the area to the right of the tabled value, from 0.995 down to 0.001, and rows cover df 1–30, 40, 50, 60, 70, 80, 90 and 100. The columns with large right-tail areas (0.995 to 0.90) hold small values from the left end of the distribution, which are needed for confidence intervals for a variance and for left-tailed variance tests. Under each α heading, the left-area row gives the same value as a percentile: the 0.95 column, for example, is the 5th percentile. For any other df or α, or to get an exact p-value, use the lookup above the table.
How to read the chi-square table
- Compute the degrees of freedom: k − 1 for a goodness-of-fit test with k categories, or (rows − 1)(columns − 1) for a test of independence.
- Choose the right-tail area. Goodness-of-fit and independence tests are right-tailed, so the column is simply your α.
- Find the df row and the α column.
- Read the critical value where they meet.
- Reject H₀ if your χ² statistic is greater than the critical value; otherwise fail to reject it.
Examples
Goodness of fit for a die
Problem. A die is rolled 120 times, and a goodness-of-fit test against equal probabilities gives χ² = 12.5. Is there evidence the die is unfair at α = 0.05?
- 01Six faces, so df = 6 − 1 = 5.
- 02Row 5, column 0.05: the critical value is 11.070.
- 03Compare: 12.5 > 11.070.
Answer. Reject H₀ at the 5% level: the counts are not consistent with a fair die (the exact p-value is about 0.029).
Test of independence
Problem. A 3 × 4 contingency table is tested for independence at α = 0.01. What is the critical value?
- 01df = (3 − 1)(4 − 1) = 6.
- 02Row 6, column 0.01: 16.812.
Answer. Reject independence only if χ² > 16.812.
Confidence interval for a variance
Problem. A sample of n = 10 has variance s² = 4.0. Find a 95% confidence interval for the population variance σ².
- 01df = n − 1 = 9. A 95% interval uses the right-tail areas 0.025 and 0.975.
- 02Row 9 gives 19.023 in the 0.025 column and 2.700 in the 0.975 column.
- 03Lower limit: (9 × 4.0) / 19.023 = 1.892. Upper limit: (9 × 4.0) / 2.700 = 13.33.
Answer. The 95% confidence interval for σ² is about 1.89 to 13.33, so the interval for σ is about 1.38 to 3.65.
Finding a p-value from the chi-square table
A printed table cannot give an exact p-value, but it can bracket one. Go to your df row, find the two tabled values your χ² statistic falls between, and read their column headings: the p-value lies between those two right-tail areas.
Example: χ² = 12.5 with df = 5. Row 5 shows 11.070 under 0.05 and 12.833 under 0.025. Because 11.070 < 12.5 < 12.833, the p-value is between 0.025 and 0.05, so the result is significant at α = 0.05 but not at α = 0.025. The exact p-value is 0.0285. If your statistic is beyond the last column, report p < 0.001; if it is below the 0.10 column, report p > 0.10. Type the statistic into the lookup above, or use the P-Value from Chi-Square Calculator, for the exact value.
Most-used chi-square critical values (df 1–10)
These are the values most chi-square tests need: right-tailed critical values for small df at the four common significance levels. The df = 1, α = 0.05 value of 3.841 is 1.96², the square of the two-tailed z critical value, because a χ² variable with 1 df is a squared standard normal.
| df | α = 0.10 | α = 0.05 | α = 0.025 | α = 0.01 |
|---|---|---|---|---|
| 1 | 2.706 | 3.841 | 5.024 | 6.635 |
| 2 | 4.605 | 5.991 | 7.378 | 9.210 |
| 3 | 6.251 | 7.815 | 9.348 | 11.345 |
| 4 | 7.779 | 9.488 | 11.143 | 13.277 |
| 5 | 9.236 | 11.070 | 12.833 | 15.086 |
| 6 | 10.645 | 12.592 | 14.449 | 16.812 |
| 7 | 12.017 | 14.067 | 16.013 | 18.475 |
| 8 | 13.362 | 15.507 | 17.535 | 20.090 |
| 9 | 14.684 | 16.919 | 19.023 | 21.666 |
| 10 | 15.987 | 18.307 | 20.483 | 23.209 |
Right-tail and left-tail values
The column headings are right-tail areas. A heading of 0.05 means 5% of the distribution lies above the tabled value, so it is the critical value for a right-tailed test at α = 0.05. A heading of 0.95 means 95% lies above the value, so it cuts off the lowest 5% and is the critical value for a left-tailed test at α = 0.05.
For a two-sided interval or test at level α, use two columns: α/2 for the upper cutoff and 1 − α/2 for the lower one. With df = 5, the 95% pair is 0.831 and 12.833.
Degrees of freedom for chi-square procedures
Goodness-of-fit and independence tests rely on adequate expected counts, commonly at least 5 per cell, for the χ² approximation to hold. Find exact critical values with the Chi-Square Critical Value Calculator, run the full tests with the Chi-Square Goodness of Fit Calculator and the Chi-Square Test of Independence Calculator, or turn a statistic into a p-value with the P-Value from Chi-Square Calculator.
| Procedure | Degrees of freedom | Tail |
|---|---|---|
| Goodness of fit with k categories | k − 1, minus one more for each parameter estimated from the data | Right |
| Independence or homogeneity in an r × c table | (r − 1)(c − 1) | Right |
| Test or confidence interval for one variance | n − 1 | Right, left or both |
Print or download the chi-square table
Use Download PDF at the top of the page for a printable copy: the chi-square table is Table 3 of the free Statculator statistical tables PDF, which also holds the z, t, F and Pearson r tables. Print / save as PDF prints this page with the full table and no scroll box.
Every value is computed from the exact chi-square inverse CDF and rounded to three decimals, so it can differ from older printed tables in the last digit. You can check any entry against the NIST/SEMATECH e-Handbook table of chi-square critical values, which uses the same right-tail convention; its chi-square distribution page gives the formulas.
Frequently asked questions
How do you read a chi-square table?
Why are chi-square tests right-tailed?
What does the 0.95 column in a chi-square table mean?
How do I find the degrees of freedom for a chi-square test of independence?
What is the chi-square critical value for df = 1 at α = 0.05?
How do you find a p-value with a chi-square table?
What if my degrees of freedom are larger than 100?
Cite this page
Statculator. (2026, November 14). Chi-Square Table (χ² Distribution Table). Retrieved November 14, 2026, from https://statculator.com/tables/chi-square-table/
Skip the table: exact calculators
- Chi-Square Critical Value Calculatorχ² critical values for right, left and two-tailed tests.
- Chi-Square Test of Independence CalculatorChi-square test of independence for any r × c table, with expected counts, steps and Cramér’s V.
- Chi-Square Goodness of Fit CalculatorTest whether observed counts match expected counts or proportions.
- P-Value from Chi-Square CalculatorRight-tail (or left/two-tail) p-value for a χ² statistic.
Values are computed from the exact distribution functions used by Statculator’s calculators (see methodology).