Chi-Squared Distribution Basics
What You'll Learn
You'll understand how the chi-squared distribution arises from normal variables, its key properties, and why degrees of freedom matter.
The Core Idea
The chi-squared distribution emerges naturally when you square standard normal random variables and add them up. If you have k independent standard normal variables Z₁, Z₂, ..., Zₖ (each with mean 0 and variance 1), then the sum of their squares follows a chi-squared distribution with k degrees of freedom:
χ²(k) = Z₁² + Z₂² + ... + Zₖ²
Think of it this way: squaring a normal variable always gives a non-negative result, so chi-squared distributions are always positive (no negative values possible). The parameter k — the degrees of freedom — tells you how many independent squared normals you're summing.
Key Properties
- Support: χ² ≥ 0 (only non-negative values)
- Shape: Right-skewed, especially for small k; becomes more symmetric as k increases
- Mean: E[χ²(k)] = k
- Variance: Var[χ²(k)] = 2k
- As k → ∞: The distribution approaches normality (thanks to the Central Limit Theorem)
Connection to Sample Variance
This distribution is crucial for statistical inference. When estimating a population variance from a sample, the statistic (n-1)S²/σ² follows a chi-squared distribution with (n-1) degrees of freedom. This forms the foundation for variance tests and confidence intervals.
The "degrees of freedom" represent the number of independent pieces of information contributing to the distribution—analogous to how the t-distribution's degrees of freedom related to sample size.
Key Takeaway: The chi-squared distribution with k degrees of freedom is the distribution of the sum of k independent squared standard normal variables; it's always positive, right-skewed for small k, and fundamental for testing variances and categorical data relationships.