Overview
The F statistic compares the variation between groups with the variation within them. It's the test statistic in ANOVA and in regression's overall significance test.
Enter the between-group and within-group sums of squares with their degrees of freedom, and your alpha. You get the exact p-value from the F distribution.
Worked examples
| Inputs | Result |
|---|---|
| SS Between460DF Between3SS Within980DF Within44Alpha (%)5 | MS between: 153.33MS within: 22.27F-statistic: 6.88p-value: 0.000668Significant at alpha=5% |
Show 2 more examples
| SS Between120DF Between2SS Within600DF Within27Alpha (%)5 | MS between: 60MS within: 22.22F-statistic: 2.7p-value: 0.09Not significant at alpha=5% |
| SS Between50DF Between4SS Within1,000DF Within95Alpha (%)5 | MS between: 12.5MS within: 10.53F-statistic: 1.19p-value: 0.32Not significant at alpha=5% |
MS between by DF between
With the calculator's starting values, the MS between is 153.33. The table shows how it changes with the DF between.
| DF Between | MS between |
|---|---|
| 1.5 | 306.67 |
| 2 | 230 |
| 2.5 | 184 |
| 3starting value | 153.33 |
| 3.5 | 131.43 |
| 4 | 115 |
| 4.5 | 102.22 |
Other inputs: SS Between: 460 · SS Within: 980 · DF Within: 44 · Alpha: 5%. Change them in the calculator above for your own numbers.
How it works
Each sum of squares divided by its degrees of freedom gives a mean square. F is the between mean square divided by the within mean square. If the groups really don't differ, F tends to be close to 1. The p-value comes from the F distribution with both degrees of freedom.
The formula
| MS | Mean square: sum of squares ÷ degrees of freedom |
Practical tips
- 460 on 3 df and 980 on 44 df give F = 6.88, well above the 5% critical value of about 2.82.
- In Excel, =F.DIST.RT(F, df1, df2) gives the exact p-value, and =F.INV.RT(0.05, df1, df2) gives the critical value.
- F can't be negative, because both mean squares are positive.
Frequently asked questions
What is a large F?
It depends on the degrees of freedom. With more data, smaller F values become significant.
Where do the sums of squares come from?
From an ANOVA table in statistics software, or by working through the group means by hand.
How is the p-value worked out?
From the F distribution with your two degrees of freedom.