Course contentsShow
← Mathematics
Lesson 2925 of 3,12157. Common DistributionsFree lesson

The F-Distribution: Definition and Derivation

Define the F-distribution as the ratio of two scaled chi-squared variables with degrees of freedom ν₁ and ν₂.

The F-Distribution: Definition and Derivation

What you'll learn: You'll understand how the F-distribution arises as the ratio of two independent chi-squared random variables, each scaled by their degrees of freedom.

The Core Idea

The F-distribution is a continuous probability distribution that emerges naturally when we compare the variability of two independent samples. Specifically, it's constructed from two chi-squared random variables.

If you have two independent chi-squared random variables:

  • χ₁² with ν₁ degrees of freedom
  • χ₂² with ν₂ degrees of freedom

Then the random variable:

F = (χ₁² / ν₁) / (χ₂² / ν₂)

follows an F-distribution with degrees of freedom ν₁ and ν₂, written as F ~ F(ν₁, ν₂).

Why Scale by Degrees of Freedom?

Think of it this way: each chi-squared variable accumulates "randomness" proportional to its degrees of freedom. By dividing each by its degrees of freedom, we're creating a per-degree-of-freedom variance. The F-distribution then compares these normalized variances.

The first degrees of freedom (ν₁) is called the numerator degrees of freedom, and the second (ν₂) is the denominator degrees of freedom.

Practical Context

This distribution is fundamental in analysis of variance (ANOVA) and comparing sample variances. When testing whether two populations have equal variances, the ratio of sample variances (properly scaled) follows an F-distribution under the null hypothesis.

Key Takeaway: The F-distribution is defined as the ratio F = (χ₁²/ν₁)/(χ₂²/ν₂), where χ₁² and χ₂² are independent chi-squared random variables with degrees of freedom ν₁ and ν₂, providing a probability model for comparing scaled variances.