This seems to work on a case by case scenario, but I wanted to see if there's some generic way or thought process I can go through to find the joint distribution of 2 dependent random variables if I know their marginal distributions. In some cases, perhaps you can determine this through conditional probabilities, but what if we have no knowledge of conditional probability?

For example, say $X_1$ and $X_2$ are uniformly distributed on $[0,1]$. Say we define $Y = \min(X_1, X_2)$ and $Z = \max(X_1, X_2)$. To determine $P(Y \geq y, Z \leq z)$, you could draw a picture.

  • 2
    $\begingroup$ You can get the proper font and spacing for $\min$ and $\max$ using \min and \max. For operators that don't have a command of their own, you can use \operatorname{name}. $\endgroup$ – joriki May 6 at 5:54

The joint distribution is not determined by the marginal distributions. For instance, if $X_1$ and $X_2$ are uniformly distributed on $[0,1]$, two extremes would be that $X_1$ and $X_2$ could be independent, or you could have $X_1=X_2$. The joint distribution cannot be determined without further information (such as the conditional probabilities).

| cite | improve this answer | |

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.