3
$\begingroup$

Suppose $X$ and $Y$ are random variables. As I understood it, mean independence is defined as follows

$Y$ is mean-independent of $X$ iff $\Bbb E[Y|X] = \Bbb E[Y]$

But my professor in class gave the following definition in class yesterday

$Y$ is mean-independent of $X$ iff $\Bbb E[Y|X] = c$, where $c \in \Bbb R$

Is this the same thing?

Like suppose $\Bbb E[Y|X] = c$, where $c \ne \Bbb E[Y]$.

EDIT:

Actually, my last statement can't be true by the law of iterated expectations since

$$E_X[E[Y|X]] = E[Y]$$

And by that law, then if $E[Y|X] = c$, $E_X[E[Y|X]] = E[Y] = c$

$\endgroup$

2 Answers 2

3
$\begingroup$

This is indeed the same thing, and follows from the properties of conditional expectation:

$$E[Y|X]=c$$

implies

$$E[Y]=E[E[Y|X]]=E[c]=c.$$

$\endgroup$
1
$\begingroup$

The notation of your professor means that E[Y|X] is a constant value, which does not depend of X, so Y is mean-independent of X.

$\endgroup$

Your Answer

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

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