Zhaolu

Zhao Lü

code · read · fitness

Posts
Portfolio
Photos
Teach
Travels
Talks & Patents

Recent Posts

  • VLM Grounding on a Mac: Image In, Boxes Out 2026-11-16
  • Unlimited-OCR-2 on Dual-Panel Lab Tables: What Works, What Breaks, How I Fixed It 2026-11-16
  • JA4 Fingerprinting: Why One Digest Can Cover Hundreds of User-Agents 2026-11-16
Read more posts →
CS Glossary / Sample variance

Sample variance

Also known as: Empirical variance, S-squared

The sample variance with Bessel correction is

\[S^2=\frac{1}{n-1}\sum_{i=1}^n(X_i-\bar X)^2.\]

The $n-1$ degrees of freedom account for estimating $\mu$ by $\bar X$; $S^2$ is unbiased for $\sigma^2$ in the iid finite-variance case. The MoM/MLE version divides by $n$ and is biased low by $\sigma^2/n$ under Normality.

Related terms

  • Variance
  • Sample mean
  • Degrees of freedom
  • Unbiased estimator
  • Maximum likelihood

← Back to CS Glossary