edited by
698 views
13 votes
13 votes

Suppose we wish to calculate $P(H \mid E 1, E 2),$ and we have no conditional independence information.

Which of the following sets of numbers are sufficient for the calculations?

  1. $P(E 1, E 2), P(H), P(E 1 \mid H), P(E 2 \mid H)$
  2. $P(E 1, E 2), P(H), P(E 1, E 2 \mid H)$
  3. $P(H), P(E 1 \mid H), P(E 2 \mid H)$
  4. $P(H), P(E 1 \mid H)$
edited by

4 Answers

12 votes
12 votes
We do not have any independence assumptions:
$$
P\left(H \mid E_1, E_2\right)=\left(P\left(E_1, E_2 \mid H\right) P(H)\right) / P(E 1, E 2)
$$
So we need to know these probabilities: $P(H), P\left(E_1, E_2 \mid H\right)$ and $P\left(E_1, E_2\right)$, which is B.
0 votes
0 votes
P(H|E1,E2)=P(H,E1,E2)/P(E1,E2)=P(H∩E1∩E2)/P(E1∩E2)=P(H∩(E1∩E2))/P(E1∩E2)={P((E1∩E2)|H)*P(H)}/P(E1∩E2)={P((E1,E2)|H)*P(H)}/{P(E1,E2)}

Now this cannot be further broken.

So D is correct option.
Answer:

Related questions

14 votes
14 votes
2 answers
3
GO Classes asked Apr 12, 2023
1,242 views
$A$ and $B$ are two events. If $P(A, B)$ decreases while $P(A)$ increases, what must be true:$P(A \mid B)$ decreases$P(B \mid A)$ decreases$P(B)$ decreasesAll of above
10 votes
10 votes
2 answers
4