I'm trying to better understand the chain rule of conditional probability. I haven't seen it explicitly confirmed anywhere, but I'd like to know if every factorization of the joint distribution is valid?

For example:

P(A,B,C) = P(A|B,C)*P(B|C)*P(C)
         = P(A|B,C)*P(C|B)*P(B)
         = P(C|A,B)*P(B|A)*P(A)

Set intersection is associative and commutative: $A\cap B\cap C=A\cap(B\cap C)=A\cap(C\cap B)=\dots =C\cap(B\cap A)$. Therefore the answer is: yes :)

For example: $$P(A,B,C)=P(C,(B,A))=P(C|B,A)P(B,A)=P(C|B,A)P(B|A)P(A)$$
In general, $$P(X_1,\dots,X_n)=\prod_{j=1}^nP(X_j\mid X_1,\dots,X_{j-1})$$ where $(X_1,\dots,X_n)$ can be in any order.

  • $\begingroup$ Awesome, thank you! $\endgroup$ – jbuddy_13 Sep 10 '20 at 22:49

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.