0
$\begingroup$

Where X is a regressor and Y is the dependent variable. I know that if E[XY]=E[X]E[Y] then X and Y are independent, hence uncorrelated but I don’t get what E[XY]=0 means.

$\endgroup$
3
  • $\begingroup$ A bit more context would help. Is $E[XY]=0$ an assumption or a result? The same goes for $E[Y]=0$. $\endgroup$
    – Herr K.
    Jun 16 at 15:53
  • 3
    $\begingroup$ If $X$ and $Y$ are independent then $E[XY]=E[X]E[Y]$ but not conversely. $\endgroup$
    – Bertrand
    Jun 16 at 16:37
  • $\begingroup$ Yes sorry, I made a mistake and it’s not E[Y]=0 but, again, E[XY]. Also, exactly, E[XY]=0 is an assumption. $\endgroup$ Jun 16 at 22:02

1 Answer 1

2
$\begingroup$

I think this is a very fundamental confusion. $E[XY]$ means that the result of $X*Y$ should average together to be 0. Relevant operators are $E()$, which is average.

Implications can be very far reaching, but most notably is that (as mentioned above) if $E[XY] \neq E[X]*E[Y]$ then $X$ and $Y$ are not independent. It is a good mental exercise to attempt to see if you can construct a minimal working example of variables that are independent or dependent.

$\endgroup$
0

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

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