Bessel’s Correction

Bessel’s correction is an approach to reduce the Bias due to finite sample size.

In statistics, it’s the use of instead of in the formula for the sample variance and sample standard deviation.

Proof of Bessel’s Correction

From ChatGPT.

Let be i.i.d. samples from a population with mean and variance .

Define:

  • The sample mean:

  • The sample variance:

We now prove that , i.e., this estimator is unbiased.


Step 1: Expand the squared term

Note that:


Step 2: Take expectation

Take the expectation of both terms:

  • Since , we have:

  • For , we use:

So:

Putting it all together:


Step 3: Divide by

Since

Taking expectation:

✅ Hence, the sample variance with denominator is an unbiased estimator of the population variance.