0
$\begingroup$

This question already has an answer here:

I am looking to understand the intuition behind moments of random variables.

I understand the first moment relating to the mean and the second one relating to the variance. But what use does the n-th moment have?

Thank you

$\endgroup$

marked as duplicate by Hans Lundmark, Community May 22 '18 at 14:58

This question has been asked before and already has an answer. If those answers do not fully address your question, please ask a new question.

0
$\begingroup$

Probably you also know that the third moment the asymmetry of the distribution (skewness), and the fourth moment tells you how the tails are behaved (kurtosis). But perhaps you can get some insight from the moment generating function

$$ M_X(t) = \mathbb{E}\left[e^{tX}\right] = \mathbb{E}\left[\sum_k \frac{t^k}{k!}X^k\right] = \sum_k \frac{t^k}{k!}\mathbb{E}[X^k] = \sum_k \frac{t^k}{k!}\left.\frac{{\rm d}^k M(t)}{{\rm d}t^k}\right|_{t=0} $$

If you know all moments $\mathbb{E}[X^k]$ (or equivalently $M_X(t)$) you could try to invert the problem and actually estimate the underlaying PDF, this is know as the moment problem

$\endgroup$

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