Dies ist ein Nachtrag zu @ Macros sehr netter Antwort, die genau beschreibt, was bekannt sein muss, um die Varianz des Produkts zweier korrelierter Zufallsvariablen zu bestimmen. Seit
var(XY)=E[(XY)2]−(E[XY])2=E[(XY)2]−(cov(X,Y)+E[X]E[Y])2=E[X2Y2]−(cov(X,Y)+E[X]E[Y])2=(cov(X2,Y2)+E[X2]E[Y2])−(cov(X,Y)+E[X]E[Y])2(1)(2)(3)
where
cov(X,Y),
E[X],
E[Y],
E[X2], and
E[Y2] can be assumed to
be known quantities, we need to be able to determine the value of
E[X2Y2] in
(2) or
cov(X2,Y2) in
(3).
This is not easy to do in general, but, as pointed out already, if
X and
Y are
independent random variables, then
cov(X,Y)=cov(X2,Y2)=0cov(X,Y)0E[X2Y2] or
cov(X2,Y2) even though it
does simplify the right sides of
(2) and
(3) a little.
When X and Y are dependent
random variables, then in at least one (fairly common
or fairly important) special
case, it is possible to find
the value of E[X2Y2] relatively easily.
Suppose that X and Y are jointly normal random variables
with correlation coefficient ρ. Then, conditioned
on X=x, the conditional density of Y is a normal
density with mean
E[Y]+ρvar(Y)var(X)−−−−−√(x−E[X]) and variance var(Y)(1−ρ2). Thus,
E[X2Y2∣X]=X2E[Y2∣X]=X2⎡⎣var(Y)(1−ρ2)+(E[Y]+ρvar(Y)var(X)−−−−−−−√(X−E[X]))2⎤⎦
which is a
quartic function of
X, say
g(X), and the Law of Iterated
Expectation tells us that
E[X2Y2]=E[E[X2Y2∣X]]=E[g(X)](4)
where the right side of
(4) can be computed from knowledge of the
3rd and 4th moments of
X -- standard results that can be found
in many texts and reference books
(meaning that I am too lazy to look them up
and include them in this answer).
Further addendum: In a now-deleted answer, @Hydrologist gives the variance of XY as
Var[xy]=(E[x])2Var[y]+(E[y])2Var[x]+2E[x]Cov[x,y2]+2E[y]Cov[x2,y]+2E[x]E[y]Cov[x,y]+Cov[x2,y2]−(Cov[x,y])2(5)
and claims that this formula is from two papers published a half-century ago in JASA. This formula is an incorrect transcription of the results in the paper(s) cited by Hydrologist. Specifically,
Cov[x2,y2] is a mistranscription of
E[(x−E[x])2(y−E[y])2] in the journal article, and similarly for
Cov[x2,y] and
Cov[x,y2].