Given random variable $X \sim Normal(\mu_x, \sigma_x)$ and $Y = X + 1$, how can I calculate their normalized correlation coefficient?

I know the formulas:

$Corr(X, Y) = \frac{Cov(X, Y)}{\sqrt{\sigma_x^2 * \sigma_y^2}}$

$Cov(X, Y) = E[XY] - E[X]E[Y]$

In order to simplify the covariance calculation I need to establish whether the variables are independent or dependent. What can I say about their relationship? It seems like they are dependent given their definition, but if I look at their PDFs it seems like they are independent:

$X \sim Normal(\mu_x, \sigma_x)$

$Y \sim Normal(\mu_x + 1, \sigma_x)$

Considering $\mu_x$ is a constant value I can write $\mu_y = \mu_x + 1$, which will produce another constant, and I can rewrite Y:

$Y \sim Normal(\mu_y, \sigma_x)$

In essence I have 2 normally distributed random variables X and Y located at $\mu_x$ and $\mu_y$ respectively, which are independent. This logic seems right to me, but having chatted on #math I found strong disagreement without any explanation.

Could you please clear this fog in my head? =)


You could use these properties \begin{eqnarray} \mathbb{C}{\rm ov}[X,Y] &=& \mathbb{C}{\rm ov}[X,X + 1] = \mathbb{C}{\rm ov}[X,X] = \sigma_x^2 \end{eqnarray}


$$ \mathbb{C}{\rm orr}[X,X + 1] = 1 $$

  • $\begingroup$ Do these properties hold for both dependent and independent variables? $\endgroup$ – NindzAI Oct 20 '17 at 19:25
  • $\begingroup$ @NindzAI Correct $\endgroup$ – caverac Oct 20 '17 at 19:29

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.