Can someone explain me what the relation is between bivariate normal distribution and dependence and independence of two variables? When i search for this topic i get answer in dependence and independence of two variables :(


If you know that $X$ and $Y$ are jointly a bivariate normal distribution then $X$ and $Y$ are independent if and only if they are uncorrelated.

However, the above statement is contingent on $X$ and $Y$ having a bivariate normal distribution. If all we know are the following facts:

  1. The marginal distributions of $X$ and $Y$ are normally distributed.

  2. The variables are uncorrelated.

Then it is possible to construct examples where the variables are not independent of each other. (Also see https://en.wikipedia.org/wiki/Normally_distributed_and_uncorrelated_does_not_imply_independent for an example.)

  • $\begingroup$ +1 This was very well done and exactly what I would have said. $\endgroup$ – Michael Chernick Dec 15 '16 at 14:52
  • $\begingroup$ @whuber The link to cardinal's beautiful answer that you inserted via your edit might not be completely relevant here since, to the best of my belief, none of the 6 examples in cardinal's answer has uncorrelated but independent marginally normal random variables; they are all instances of marginally normal but not jointly normal random variables $\endgroup$ – Dilip Sarwate Dec 15 '16 at 16:58

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.