1
$\begingroup$

This was asked as an self-assessment question, that I was quite embarrased by, as I had no idea how to start it...

Consider two random variables X and Y that are allowed to be correlated and whose first and second moments are assumed to be finite. Show that:

$$Var(Y) = \mathbf{E}_{x}[Var(Y|X)] + Var(\mathbf{E}_{y|x}[Y|X])$$

where $\mathbf{E}_{X}$ and $\mathbf{E}_{y|x}$ denote expectations with respect to the marginal distribution of X and the conditional distribution of Y , given X, respectively.

Improve this question
$\endgroup$

1 Answer 1

Reset to default
1
$\begingroup$

$Var(Y)=EY^2-(EY)^2=E(E(Y^2|X))-(E(E(Y|X)))^2=E(Var(Y|X))+E((E(Y|X))^2)-(E(E(Y|X)))^2=E(Var(Y|X))+Var(E(Y|X))$

Improve this answer
$\endgroup$
1
  • $\begingroup$ Use itterated expectations - brilliant. Thank you for this. $\endgroup$
    – user73315
    Commented Apr 11, 2015 at 19:27

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.