Calculating Variance of sample variance

889 Views Asked by At

How do you find the variance of sample variance, without using moment generating functions but using the fact that variance of a chi squared distribution with n degrees of freedom, is equal to 2n?

Sample variance is defined as $$S^2=\frac1{n-1}\sum_{i=1}^n\left(X_i-\overline{X}\right)^2.$$

1

There are 1 best solutions below

0
On

Use Fisher's Lemma: $\frac{(n-1)s^2}{\sigma^2} \sim \chi^2_{n-1}$

So $\mathbb{D} \left( \frac{(n-1)s^2}{\sigma^2} \right) = \mathbb{D} \chi^2_{n-1} = 2(n-1)$

$\frac{(n-1)^2 \mathbb{D}(s^2)}{\sigma^4} = 2(n-1) \Rightarrow \boxed{\mathbb{D}(s^2) = \frac{2\sigma^4}{n-1}}$