Bessel's Correction — Definition, Formula & Example
Bessel's correction is the practice of dividing by instead of when you compute the variance of a sample. Without it, sample variances would come out too small on average.
For independent observations from a population with variance , the sum of squared deviations from the sample mean has expected value . Dividing that sum by makes an unbiased estimator of . Dividing by instead gives an estimator with expected value , which is biased low. The factor is the number of degrees of freedom left after estimating the mean from the data.
Key Formula
Where:
- = Sample variance with Bessel's correction
- = Number of observations in the sample
- = The i-th observation
- = Sample mean
- = Population variance being estimated
- = Expected value, the long-run average over all possible samples
Worked Example
Problem: A population consists of the three values 2, 4, 6. List all 9 ordered samples of size 2 drawn with replacement, so the two draws are independent. Average the sample variances computed with , then average them again computed with . Compare both averages to the population variance .
Step 1: Find the population mean and the population variance. Divide by , because this is the whole population.
Step 2: For a sample , the mean is . The two deviations are , so the sum of squared deviations is . Sort the 9 samples by their SS value.
Step 3: With , dividing by leaves each SS unchanged. Dividing by halves it. Average each version over all 9 samples.
Answer: The version averages exactly , which equals , so it is unbiased. The divide-by- version averages . That is only of the true variance, so it systematically underestimates the spread.
Why It Matters
In AP Statistics, every one-sample and two-sample t-procedure uses computed with . For one-sample t-procedures, the t-distribution has degrees of freedom for the same reason. On a TI-84, the 1-Var Stats output labeled Sx uses Bessel's correction, while σx does not. You need to pick the right one for sample data.
Common Mistakes
Mistake: Believing that Bessel's correction also makes the sample standard deviation an unbiased estimator of .
Correction: The correction only makes unbiased for . Taking a square root does not preserve averages, so is still true. The leftover bias is small for moderate , and AP Statistics procedures simply use as is.
