Chi-Square CalculatorChi-Square Calculator
Values

Chi-Square Critical Value Calculator

Enter the degrees of freedom and your significance level. The calculator gives the χ² value your statistic must exceed, and the lower and two-tailed values for variance tests.

Upper critical value (right tail 0.05)3.8415
Lower critical value (left tail 0.05)0.0039
Two-tailed, 0.025 in each tail0.0010 and 5.0239
010.8χ² = 3.841

Reject the null hypothesis of a chi-square test of independence or goodness of fit at the 5% level when χ² is larger than 3.8415. The lower and two-tailed values are for tests about a variance.

Reproduce this result in R or Python

R

qchisq(0.05, df = 1, lower.tail = FALSE)   # upper critical value
qchisq(0.05, df = 1)                       # lower critical value

Python (SciPy)

from scipy.stats import chi2
print(chi2.isf(0.05, 1))   # upper critical value
print(chi2.ppf(0.05, 1))   # lower critical value

Checked on November 21, 2026. Results computed by our statistics engine, version 1.0.0.

On this page

What a critical value is

The critical value is the point on the chi-square distribution with a chosen area to its right. With 1 degree of freedom and α = 0.05 it is 3.8415: a test of a 2x2 table is significant at the 5% level exactly when χ² is larger than that. Comparing χ² with the critical value and comparing p with α always give the same decision.

Common critical values

dfα = 0.10α = 0.05α = 0.01α = 0.001
12.7063.8416.63510.828
24.6055.9919.21013.816
36.2517.81511.34516.266
47.7799.48813.27718.467
59.23611.07015.08620.515
1015.98718.30723.20929.588

Each value is computed by the calculator's engine. Our test suite checks the rows for 1 and 100 degrees of freedom against the NIST/SEMATECH e-Handbook table, and they agree to all three printed decimals (NIST critical values). The full chi-square table goes from 1 to 100 degrees of freedom and on to 1000.

Finding your degrees of freedom

  • Test of independence or homogeneity: (rows − 1) times (columns − 1). A 2x3 table has 2.
  • Goodness of fit: categories minus 1, minus one more for each parameter estimated from the data.
  • McNemar test: 1.
  • Test of a variance: n − 1 for a sample of n.

Lower and two-tailed values

Tests of independence and fit only ever reject for large χ², so they use the upper critical value. The chi-square test for a single variance is different: a sample variance much smaller or much larger than the hypothesized one both count against the null. For a two-tailed test at α = 0.05 with 10 degrees of freedom, reject when χ² is below 3.247 or above 20.483. The calculator shows these alongside the upper value.

How the values are computed

There is no closed formula for chi-square quantiles. We start from the Wilson-Hilferty approximation and refine with Newton steps on the exact upper tail until the answer stops changing, which gives about twelve correct significant figures, the same as R's qchisq and SciPy's chi2.isf. For large degrees of freedom the value approaches df + z√(2 df): at 100 degrees of freedom and α = 0.05 the exact value is 124.342, against 123.262 from that rough normal approximation.

Common questions

What is the chi-square critical value for 1 degree of freedom?

3.841 at α = 0.05, 6.635 at 0.01 and 10.828 at 0.001.

Is a larger χ² always more significant?

For the same degrees of freedom, yes. Across different df, compare p-values instead, because the critical value rises with df.

Sources