- #1
logarithmic
- 107
- 0
Does anyone know the formula for an unbiased estimator of the population variance [tex]\frac{1}{n}\sum_{i=1}^{n}(x_i - \bar{x})^2[/tex] when taking r samples without replacement from a finite population [tex]\{x_1, \dots, x_n\}[/tex] whose mean is [tex]\bar{x}[/tex]?
A google search doesn't find anything useful other than the the special cases of when r = n the estimator is of course [tex]\frac{r-1}{r}s^2[/tex], where [tex]s^2 = \frac{1}{r-1}\sum_{i=1}^{r}(x_i - \bar{x})^2[/tex] which is of course the unbiased estimator when taking r samples with replacement.
I know that a (relatively) simple formula exists, I've seen it somewhere before, just don't remember where.
A google search doesn't find anything useful other than the the special cases of when r = n the estimator is of course [tex]\frac{r-1}{r}s^2[/tex], where [tex]s^2 = \frac{1}{r-1}\sum_{i=1}^{r}(x_i - \bar{x})^2[/tex] which is of course the unbiased estimator when taking r samples with replacement.
I know that a (relatively) simple formula exists, I've seen it somewhere before, just don't remember where.
Last edited: