What does it mean for a random variable to have finite second order moments?

2.9k Views Asked by At

I'm trying to digest some litterature in time series analysis and don't quite understand what it means for a random variable to have finite second order moments. Tried to look it up in a probability theory textbook, however I don't quite get the intuition.

Thanks in advance!

1

There are 1 best solutions below

2
On BEST ANSWER

The $k$-th moment of a random variable $X$ is $E(X^k)$. We say that this moment exists if $E(|X|^k)$ is a finite value (note the absolute value). If a r.v. has a finite $K$-th moment, the moments $k \le K$ are also finite. This property comes from the fact that the probability of the universe, the whole probability space, is $1$ and can be further justified by the comment by James Martin below this answer.

The variance is $Var(X) = E(X^2)-E(X)^2 = E(X^2)-E(X^1)^2 $. By the definition above and the property, if $X$ has a finite 2nd order moment, it has a variance (and conversely).