Skip to content
Statculator
P-Values & Critical Values

F Critical Value Calculator

Free F critical value calculator and F table. Get the critical F for any df1, df2 and α, right-, left- or two-tailed, for ANOVA and regression, with steps.

Free, no sign-up Runs in your browserBy Hira Noor, BS MathematicsUpdated

Try

ANOVA: k − 1. Regression: k predictors. Variances: n₁ − 1.

ANOVA: N − k. Regression: n − k − 1. Variances: n₂ − 1.

Usually 0.05 or 0.01.

Tail

ANOVA and regression are right-tailed. Two-tailed gives both cut-offs for comparing two variances.

Results

Critical value F* (right-tailed)
2.8663
P(F ≥ 2.8663) = 0.05, df = (3, 36)
Degrees of freedom (df₁, df₂)
(3, 36)
Significance level, α
0.05
Area in the tail
0.05
Mean of F, df₂ / (df₂ − 2)
1.0588
Median of F
0.8038
Decision rule
Reject H₀ if F ≥ 2.8663

Interpretation: An F statistic of 2.8663 or more with df = (3, 36) is significant at α = 0.05. In a one-way ANOVA this means the between-group mean square must be at least 2.87 times the within-group mean square.

f distribution curve with the shaded probability region, markers at F* = 2.866F* = 2.8660.00.51.01.52.02.53.03.54.0F distribution, df₁ = 3, df₂ = 36
Shaded: rejection region with total area α = 0.05. Dashed line: critical value.

F critical values for df = (3, 36)

αRight-tailed (α above)Left-tailed (α below)Two-tailed (α/2 each side)
0.12.24260.19370.1163 and 2.8663
0.052.86630.11630.0712 and 3.5047
0.0253.50470.07120.0441 and 4.1614
0.014.37710.03780.0236 and 5.0616
0.0055.06160.02360.0148 and 5.7695
0.0016.74360.0080.005 and 7.5115

Every left-tailed value equals 1 / (right-tailed value with df swapped to (36, 3)).

Step-by-step solution

  1. 1

    Decide where α goes

    ANOVA and regression F-tests reject H₀ only for large F, so all of α is in the right tail.

    α = 0.05 in the right tail
  2. 2

    Find the upper critical value

    Invert the F CDF numerically: find the value with the target cumulative probability.

    F_U = F⁻¹(0.95; 3, 36) = 2.8663
  3. 3

    Use the critical value

    Reject H₀ if F ≥ 2.8663

What is a F Critical Value Calculator?

An F critical value calculator finds the value of the F distribution with numerator df₁ and denominator df₂ that leaves an area α in the tail. ANOVA and regression F-tests use the right tail: for df = (3, 36) at α = 0.05 the critical F is 2.8663, so you reject H₀ when F ≥ 2.8663. A two-tailed option returns both cut-offs for comparing two variances, using F_L = 1 / F_U with the df swapped.

What the F Critical Value Calculator does

Enter df₁, df₂ and α and choose the tail. The calculator returns the critical F (or the lower and upper values), shades the rejection region on the F curve, and lists right-tailed, left-tailed and two-tailed values at six common α levels for your df pair. Because it works for any positive df, you do not have to interpolate between the widely spaced columns of a printed F-table. In effect it is an F critical value table (a critical F value chart for every df pair and α) and an F distribution calculator for quantiles, with the working shown step by step.

Compare an F statistic with the right-tailed value in a one-way or factorial ANOVA, an overall regression F-test, or a test comparing nested models. Use the two-tailed values for the F-test of two variances when the alternative is σ₁² ≠ σ₂². To calculate the p-value for an F test instead of the cut-off, use the P-Value from F Calculator.

How to use the F Critical Value Calculator

  1. Enter the Numerator df (df₁), the degrees of freedom of the mean square on top of the ratio (k − 1 in ANOVA).
  2. Enter the Denominator df (df₂), the degrees of freedom of the mean square on the bottom (N − k in ANOVA).
  3. Enter the Significance level (α) and choose the Tail. Leave it on Right unless you are comparing two variances.
  4. Read the critical F and the rejection rule. The steps show how a lower value comes from the reciprocal rule.

How to find the F critical value

To find the critical value of F by hand you need four things: the numerator df, the denominator df, the significance level α and the tail of the test. Then read the value from an F table or compute the F quantile.

  1. Work out df₁ (numerator). One-way ANOVA: k − 1 for k groups. Regression: the number of predictors k. Two variances: n₁ − 1 for the sample whose variance is on top.
  2. Work out df₂ (denominator). One-way ANOVA: N − k. Regression: n − k − 1. Two variances: n₂ − 1. The Degrees of Freedom Calculator handles each case.
  3. Choose α. 0.05 is the usual default; 0.01 is stricter.
  4. Pick the tail. ANOVA and regression F-tests are always right-tailed. A two-sided test of two variances is two-tailed.
  5. Look up the value. In the F critical value table below, go to the column for df₁ and the row for df₂. Printed tables give right-tail values only; for a two-tailed test use the α/2 table, or let the calculator return both cut-offs.

How to calculate the F value

The F value (F statistic) is a ratio of two variance estimates. The formula for the F value depends on the test, but it is always "variance explained" over "variance left over", each divided by its df. The same df₁ and df₂ are what you enter above to get the critical value. To calculate the F value from raw data, use the ANOVA Calculator for group means or the F-Test Calculator for two variances.

F value formula for each F-test
TestF value formuladf₁df₂
One-way ANOVAF = MS_between / MS_within = [SS_between / (k − 1)] / [SS_within / (N − k)]k − 1N − k
Multiple regression (overall F-test)F = MSR / MSE = [SSR / k] / [SSE / (n − k − 1)]kn − k − 1
Two variancesF = s₁² / s₂²n₁ − 1n₂ − 1

Comparing the F value with the F critical value

Compare the F statistic from your test with the critical F for the same df and α:

  • If F is greater than (or equal to) the F critical value, it lands in the rejection region. Reject H₀: the group means (or the regression coefficients) are not all equal at that α.
  • If F is less than the F critical value, do not reject H₀. This is not proof that H₀ is true; the data are simply consistent with it.
  • The decision always agrees with the p-value: F ≥ F critical exactly when p ≤ α.
  • Example: three teaching methods with 8 students each (N = 24) give SS_between = 84 and SS_within = 176.4. Then MS_between = 84 / 2 = 42, MS_within = 176.4 / 21 = 8.4 and F = 42 / 8.4 = 5.00. The F critical value for df = (2, 21) at α = 0.05 is 3.4668. Because 5.00 exceeds 3.4668, reject H₀ that the three method means are equal (p ≈ 0.0167).

F critical value formula

Critical values are quantiles of the F(df₁, df₂) distribution, F⁻¹(p; df₁, df₂).

Right-tailed (ANOVA, regression)
F_U = F⁻¹(1 − α; df₁, df₂) → reject if F ≥ F_U
Left-tailed
F_L = F⁻¹(α; df₁, df₂) → reject if F ≤ F_L
Two-tailed
F_L = F⁻¹(α/2; df₁, df₂), F_U = F⁻¹(1 − α/2; df₁, df₂)
Reciprocal rule
F⁻¹(p; df₁, df₂) = 1 / F⁻¹(1 − p; df₂, df₁)
Formula symbols
SymbolMeaning
df₁numerator degrees of freedom
df₂denominator degrees of freedom
αsignificance level
F⁻¹(p; a, b)value with cumulative probability p under F(a, b)

The reciprocal rule holds because if X has an F(df₁, df₂) distribution, 1/X has an F(df₂, df₁) distribution. It is why F-tables only need to print upper-tail values.

The F distribution is named after Ronald Fisher, who developed analysis of variance in the 1920s; George Snedecor tabulated it and named it F in 1934. Its inverse CDF has no closed form, so the calculator finds it numerically. Values here agree with the NIST/SEMATECH e-Handbook table of F critical values.

Worked example: two-tailed F critical values for two variances

Comparing two machine variances: n₁ = 10, n₂ = 15

Problem. Machine A gives n₁ = 10 parts and machine B n₂ = 15 parts. Find the critical values for a two-tailed F-test of equal variances at α = 0.05, with F = s²_A / s²_B.

  1. 01df₁ = 10 − 1 = 9 and df₂ = 15 − 1 = 14; α/2 = 0.025 goes in each tail.
  2. 02Upper critical value: F⁻¹(0.975; 9, 14) = 3.2093.
  3. 03Lower critical value via the reciprocal rule: F⁻¹(0.975; 14, 9) = 3.7980, so F_L = 1 / 3.7980 = 0.2633.
  4. 04Rejection rule: reject H₀ if F ≤ 0.2633 or F ≥ 3.2093.

Answer. The variances differ significantly at the 5% level only if s²_A / s²_B is below 0.2633 or above 3.2093. An observed ratio of 3.5, for example, would lead to rejecting H₀.

F critical value table (α = 0.05)

This F distribution table gives right-tail critical values: each entry leaves 5% of F(df₁, df₂) to its right. Columns are the numerator df₁ and rows the denominator df₂. It doubles as an ANOVA critical value table: these are the F test critical values for ANOVA and regression at α = 0.05; for example df = (3, 20) gives 3.098. For other α levels, a two-tailed or left-tailed value, or any df not listed, use the calculator above or the full F-table. The last row (df₂ = ∞) equals χ²(df₁) / df₁.

F table for α = 0.05: right-tail critical values F(0.05; df₁, df₂)
df₂ \ df₁12345678910
1161.448199.500215.707224.583230.162233.986236.768238.883240.543241.882
218.51319.00019.16419.24719.29619.33019.35319.37119.38519.396
310.1289.5529.2779.1179.0138.9418.8878.8458.8128.786
47.7096.9446.5916.3886.2566.1636.0946.0415.9995.964
56.6085.7865.4095.1925.0504.9504.8764.8184.7724.735
65.9875.1434.7574.5344.3874.2844.2074.1474.0994.060
75.5914.7374.3474.1203.9723.8663.7873.7263.6773.637
85.3184.4594.0663.8383.6873.5813.5003.4383.3883.347
95.1174.2563.8633.6333.4823.3743.2933.2303.1793.137
104.9654.1033.7083.4783.3263.2173.1353.0723.0202.978
124.7473.8853.4903.2593.1062.9962.9132.8492.7962.753
154.5433.6823.2873.0562.9012.7902.7072.6412.5882.544
204.3513.4933.0982.8662.7112.5992.5142.4472.3932.348
244.2603.4033.0092.7762.6212.5082.4232.3552.3002.255
304.1713.3162.9222.6902.5342.4212.3342.2662.2112.165
404.0853.2322.8392.6062.4492.3362.2492.1802.1242.077
604.0013.1502.7582.5252.3682.2542.1672.0972.0401.993
1203.9203.0722.6802.4472.2902.1752.0872.0161.9591.910
∞3.8412.9962.6052.3722.2142.0992.0101.9381.8801.831

F critical value table (α = 0.01)

The same layout at the stricter 1% level. Each entry leaves 1% of F(df₁, df₂) in the right tail.

F table for α = 0.01: right-tail critical values F(0.01; df₁, df₂)
df₂ \ df₁123456810
516.25813.27412.06011.39210.96710.67210.28910.051
1010.0447.5596.5525.9945.6365.3865.0574.849
129.3306.9275.9535.4125.0644.8214.4994.296
158.6836.3595.4174.8934.5564.3184.0043.805
208.0965.8494.9384.4314.1033.8713.5643.368
307.5625.3904.5104.0183.6993.4733.1732.979
407.3145.1794.3133.8283.5143.2912.9932.801
607.0774.9774.1263.6493.3393.1192.8232.632
1206.8514.7873.9493.4803.1742.9562.6632.472
∞6.6354.6053.7823.3193.0172.8022.5112.321

F critical values in Excel, R, Python and on a TI-84

Every package returns the same quantile; they differ only in whether they take the right-tail area α or the cumulative area 1 − α. The examples use df = (3, 36) and α = 0.05, which all return 2.8663.

ToolRight-tailed critical valueLeft-tailed critical value
Excel / Google Sheets=F.INV.RT(0.05, 3, 36)=F.INV(0.05, 3, 36)
Rqf(0.05, 3, 36, lower.tail = FALSE)qf(0.05, 3, 36)
Python (SciPy)f.isf(0.05, 3, 36)f.ppf(0.05, 3, 36)
TI-83 / TI-84No inverse F function: solve Fcdf(X, 1E99, 3, 36) = 0.05 for X with the equation solverSolve Fcdf(0, X, 3, 36) = 0.05 for X

Common use cases

  • Setting the rejection region for a one-way or two-way ANOVA.
  • Checking the overall significance of a multiple regression model.
  • Comparing two population variances with the F-test, for example the consistency of two machines or two lab methods.
  • Comparing nested regression models, where df₁ is the number of added parameters.

Assumptions and limitations

  • The F critical values give correct error rates only if the data are independent and normally distributed; the variance-ratio test in particular is very sensitive to non-normality. Levene’s test is a more robust check of equal variances.
  • df₁ and df₂ are not interchangeable. Swapping them gives a different critical value (except through the reciprocal rule).
  • For an observed F, the P-Value from F Calculator tells you how far past the cut-off you are, which a critical value alone does not.

Frequently asked questions

How do I find the F critical value?

You need α, the numerator df and the denominator df. For a right-tailed test, the critical value is the point with area α to its right under F(df₁, df₂), F⁻¹(1 − α; df₁, df₂). Enter the three numbers above, or use F.INV.RT(α, df₁, df₂) in Excel.

What is the F critical value for ANOVA at α = 0.05?

Use df₁ = k − 1 and df₂ = N − k. For 3 groups of 10 (df = 2, 27) it is 3.3541; for 4 groups of 10 (df = 3, 36) it is 2.8663. Reject H₀ if the ANOVA F is at least that large.

What is the formula for the F value?

The F value is a ratio of two mean squares. In one-way ANOVA, F = MS_between / MS_within, where each mean square is a sum of squares divided by its df (k − 1 and N − k). In regression, F = MSR / MSE; for two variances, F = s₁² / s₂². Compare the result with the F critical value for the same df.

What if my F value is greater than the F critical value?

If F is greater than or equal to the critical value, it falls in the rejection region, so you reject H₀ at that α; equivalently its p-value is at most α. If F is less than the critical value, you do not reject H₀.

Why is the F-test usually one-tailed?

In ANOVA and regression, any departure from H₀ makes the numerator mean square larger, so only large F values are evidence against H₀. Small F values just mean the effect is weaker than noise, so the whole of α goes in the right tail.

How do I get a lower-tail F critical value from a table?

Swap the degrees of freedom, look up the upper-tail value, and take its reciprocal: F_L(α; df₁, df₂) = 1 / F_U(α; df₂, df₁). For example, the lower 2.5% point of F(9, 14) is 1 / 3.7980 = 0.2633.

How is the F critical value related to the t critical value?

When df₁ = 1, the right-tailed F critical value equals the square of the two-tailed t critical value with df₂ degrees of freedom. For example, F⁻¹(0.95; 1, 20) = 4.3512 = 2.0860².

Cite this page

Statculator. (2026, November 14). F Critical Value Calculator. Retrieved November 14, 2026, from https://statculator.com/p-values-critical-values/f-critical-value-calculator/