1
$\begingroup$

Suppose I calculate standard deviation of a sample mean as

$ \sigma / \sqrt{n} $

where $\sigma$ is the population standard deviation and $n$ the sample size.

Have I just made an assumption that the population has normal distribution?

If so, how would this formula differ if the population distribution was exponential $e^{-x}$? Intuitively it would seem wrong as our sample might have missed a very large value on one side of the distribution only, whereas a normal distribution would have outliers on both sides?

$\endgroup$
3
$\begingroup$

Under the usual assumptions (ie. i.i.d. samples), the sample mean will have standard deviation $\dfrac{\sigma}{\sqrt{n}}$ regardless of the population distribution, because the Bienaymé formula is distribution-free. The assumption that the population is normal is only required for the distribution of the sample mean to be also exactly normally distributed.

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.