Enter a data set to compute the sample variance using n - 1 degrees of freedom, measuring dispersion for inferential statistics and hypothesis testing.
用 n−1 自由度的样本方差。
| Item | Formula / Note | Source / Standard |
|---|---|---|
| Sample variance | s^2 = sum(x_i - xbar)^2 / (n - 1), Bessel-corrected | ISO 3534-1:2006, Statistics - Vocabulary and symbols |
| Unbiasedness | E[s^2] = sigma^2; dividing by n - 1 is what makes the estimator unbiased | Cramer H., Mathematical Methods of Statistics (1946) |
| Degrees of freedom | df = n - 1 because xbar consumes one linear constraint | NIST/SEMATECH e-Handbook of Statistical Methods §1.3.5.1 |
| Sampling distribution | For a normal population, (n - 1)s^2/sigma^2 follows chi-square(n - 1) | Cochran WG (1934), The distribution of quadratic forms, PNAS |
统计指标、置信区间与样本量的测算。
样本方差 s²=Σ(xᵢ−x̄)²/(n−1):样本数据围绕均值的离散程度,分母用 n−1(贝塞尔校正)得无偏估计。
方差单位为原数据单位的平方;取平方根得样本标准差 s,量纲复原。总体方差才用 n 作分母。