This might be a naive question, but could someone please tell me how the change-of-variables technique applies to conditional cases? My intuition tells me that there is no difference.

The change-of-variables technique is usually formulated for non-conditional cases, like for finding the joint distribution of $(g_1(X_1,X_2),g_2(X_1,X_2))$ where the joint distribution of $(X_1,X_2)$ is known. My question is: is the technique the same if the conditional distribution $(X_1,X_2|Y=y)$ is known and we want to know the conditional distribution $(g_1(X_1,X_2),g_2(X_1,X_2)|Y=y)$?

$Y$ is a random variable that is not independent from $(X_1,X_2)$, it could be a function of $(X_1,X_2)$. My intuition tells me that $y$ would be treated as a constant and the technique would be the same.


Your Answer

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

Browse other questions tagged or ask your own question.