The F-Distribution

Statistics · Axiom Academy

Understanding the ratio of two chi-square distributions and its role in hypothesis testing 1. F as a Ratio of Two Chi-Square Distributions The F-distribution is constructed from two independent chi-square random variables. Specifically, if we have two chi-square variables divided by their respective degrees of freedom, their ratio follows an F-distribution. Where χ² represents chi-square distributions with degrees of freedom df₁ and df₂. This construction makes the F-distribution particularly useful for comparing variances, since sample variances are related to chi-square distributions. 2. Two Degrees of Freedom Parameters Unlike many distributions that have a single shape parameter, the F-distribution requires two degrees of freedom : df₁ (numerator degrees of freedom) and df₂ (denominator degrees of freedom). Both degrees of freedom affect the shape of the distribution. As df₁ and df₂ increase, the distribution becomes more symmetric and approaches a normal distribution. Small degrees of freedom produce highly right-skewed distributions. 3. Distribution Shape: Right-Skewed and Bounded at Zero The F-distribution has several important characteristics: Always positive: F-values cannot be negative (bounded at 0) Right-skewed: The distribution has a long tail extending to the right Asymmetric: Unlike the normal distribution, it's not symmetric about its center Shape depends on df: Both degrees of freedom parameters affect skewness 4. Mean and Statistical Properties

This is the written version of the interactive lesson above. See the full Statistics course.