2
$\begingroup$

I was working on stratified sampling for variance reduction for monte carlo estimation, and I found an odd statement from this website (link posted below).

The first line on his site is, "Intuitively, smaller samples have less variance."

I don't find this intuitive at all, especially when looking at the sample variance formula:

$$s^2 = \frac{1}{n-1} \, \sum_{i=1}^n \, \Big(X_i - \overline{X}\Big)$$

Maybe I'm missing some context for this quote, so feel free to check out his site. If someone wouldn't mind explaining what the author might have intended, that would be great.

Link: https://am207.github.io/2017/wiki/stratification.html#why-does-stratification-decrease-variance

$\endgroup$
2
  • $\begingroup$ Intuitively, I would say that it does not change with sample size if estimator is unbiased. Is the estimator you showed unbiased in your case? $\endgroup$ Apr 28, 2018 at 13:43
  • $\begingroup$ That link does not work anymore! $\endgroup$ Jun 21, 2019 at 18:56

0

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Browse other questions tagged or ask your own question.