1. ## correlation proof

Hi guys. I'm not quite sure if this belongs in here but here goes.
We must prove that $y=a+bx$ for $b<0$ is perfectly negatively correlated.
Here is what I know. I know that a correlation coefficient $r(x,y) = \frac{cov Rx,Ry}{(sigmaX)(sigmaY)}$

I have the answer but i do not get where or why there is an E in there. If anyone could explain this it would be fantastic. Thank you
Chris

2. ## Re: correlation proof

By definition of variance

$Var(Y)=E((Y-\mu)^2)$ where $\mu=E(Y)$ so the proof just substitutes into this formula where $y=a-bx$