Statistics Reference

F-Table for α = 0.01 (F Critical Values)

The α = 0.01 table holds the strict cutoffs: only 1% of a true-null F distribution lies beyond each value. It is the standard reference for highly significant ANOVA results, multiple-testing situations, and fields that demand stronger evidence before rejecting a null hypothesis.

How to Read This Table

Columns are numerator degrees of freedom (df₁), rows are denominator degrees of freedom (df₂). The critical value sits where they meet; an F statistic beyond it is significant at α = 0.01.

The ANOVA from the α = 0.05 page (df₁ = 2, df₂ = 21), now held to the 1% standard:

  1. Column 2 meets row 21 at 5.78 — versus 3.47 at α = 0.05.
  2. An observed F of 4.5 is significant at the 5% level but not at 1%.
  3. Report exact p-values alongside the verdict so readers can apply their own threshold.

Common uses of this level:

  • ANOVA and regression F-tests reported as significant at the 1% level
  • Conservative testing when several comparisons are examined at once
  • Two-tailed variance-ratio tests at the overall 2% level (0.01 per tail)

F Critical Values, Upper-Tail α = 0.01

Each cell is the value an F statistic must exceed for significance at α = 0.01 (99% confidence). The ∞ row and column are computed from the exact chi-square limits of the F distribution. Values are rounded to two decimals (fewer for the very large small-df entries).

Upper-tail F critical values at alpha = 0.01 by numerator and denominator degrees of freedom
df₂ \ df₁1234567891012152024304060120
14052500054035625576458595928598160226056610661576209623562616287631363396366
298.5099.0099.1799.2599.3099.3399.3699.3799.3999.4099.4299.4399.4599.4699.4799.4799.4899.4999.50
334.1230.8229.4628.7128.2427.9127.6727.4927.3527.2327.0526.8726.6926.6026.5026.4126.3226.2226.13
421.2018.0016.6915.9815.5215.2114.9814.8014.6614.5514.3714.2014.0213.9313.8413.7513.6513.5613.46
516.2613.2712.0611.3910.9710.6710.4610.2910.1610.059.899.729.559.479.389.299.209.119.02
613.7510.929.789.158.758.478.268.107.987.877.727.567.407.317.237.147.066.976.88
712.259.558.457.857.467.196.996.846.726.626.476.316.166.075.995.915.825.745.65
811.268.657.597.016.636.376.186.035.915.815.675.525.365.285.205.125.034.954.86
910.568.026.996.426.065.805.615.475.355.265.114.964.814.734.654.574.484.404.31
1010.047.566.555.995.645.395.205.064.944.854.714.564.414.334.254.174.084.003.91
119.657.216.225.675.325.074.894.744.634.544.404.254.104.023.943.863.783.693.60
129.336.935.955.415.064.824.644.504.394.304.164.013.863.783.703.623.543.453.36
139.076.705.745.214.864.624.444.304.194.103.963.823.663.593.513.433.343.253.17
148.866.515.565.044.694.464.284.144.033.943.803.663.513.433.353.273.183.093.00
158.686.365.424.894.564.324.144.003.893.803.673.523.373.293.213.133.052.962.87
168.536.235.294.774.444.204.033.893.783.693.553.413.263.183.103.022.932.842.75
178.406.115.184.674.344.103.933.793.683.593.463.313.163.083.002.922.832.752.65
188.296.015.094.584.254.013.843.713.603.513.373.233.083.002.922.842.752.662.57
198.185.935.014.504.173.943.773.633.523.433.303.153.002.922.842.762.672.582.49
208.105.854.944.434.103.873.703.563.463.373.233.092.942.862.782.692.612.522.42
218.025.784.874.374.043.813.643.513.403.313.173.032.882.802.722.642.552.462.36
227.955.724.824.313.993.763.593.453.353.263.122.982.832.752.672.582.502.402.31
237.885.664.764.263.943.713.543.413.303.213.072.932.782.702.622.542.452.352.26
247.825.614.724.223.903.673.503.363.263.173.032.892.742.662.582.492.402.312.21
257.775.574.684.183.853.633.463.323.223.132.992.852.702.622.542.452.362.272.17
267.725.534.644.143.823.593.423.293.183.092.962.812.662.582.502.422.332.232.13
277.685.494.604.113.783.563.393.263.153.062.932.782.632.552.472.382.292.202.10
287.645.454.574.073.753.533.363.233.123.032.902.752.602.522.442.352.262.172.06
297.605.424.544.043.733.503.333.203.093.002.872.732.572.492.412.332.232.142.03
307.565.394.514.023.703.473.303.173.072.982.842.702.552.472.392.302.212.112.01
407.315.184.313.833.513.293.122.992.892.802.662.522.372.292.202.112.021.921.80
607.084.984.133.653.343.122.952.822.722.632.502.352.202.122.031.941.841.731.60
1206.854.793.953.483.172.962.792.662.562.472.342.192.031.951.861.761.661.531.38
6.634.613.783.323.022.802.642.512.412.322.182.041.881.791.701.591.471.321.00

Other Significance Levels

The F-table overview explains degrees of freedom, the reciprocal rule for lower-tail values, and where the F distribution comes from. The other three levels each have their own full table:

Frequently Asked Questions

When should results be tested at α = 0.01 instead of 0.05?

When false alarms are expensive or when many tests inflate the chance of at least one fluke: confirmatory studies, quality-critical processes, and analyses with multiple comparisons (where 0.01 sometimes serves as an informal correction). The price is power - real effects need to be larger or samples bigger to clear the higher bar.

How much larger are the 0.01 critical values than the 0.05 ones?

Typically 40-80% larger in the table's working range, with the gap widest at small denominator degrees of freedom. F(2, 21) moves from 3.47 to 5.78 (a 67% increase); F(5, 30) moves from 2.53 to 3.70. The first row is the extreme case: F(1, 1) jumps from 161 to 4052, a reminder that single-degree-of-freedom designs have almost no power at strict levels.

A result significant at 0.05 but not 0.01 - what does that mean?

The evidence is moderate: the data would arise less than 5% but more than 1% of the time under the null hypothesis. Convention labels it 'significant' but not 'highly significant'. Rather than leaning on labels, report the exact p-value (an F of 4.5 on 2 and 21 df has p ≈ 0.024) and the effect size, letting readers weigh the evidence against their own cost of error.