The Student Room Group

Bayes Theorem

can anyone help me see where i went wrong?
(edited 9 years ago)
Original post by JJ Downey
can anyone help me see where i went wrong?

If he fails overall, there are three options, (pass, fail), (fail, pass), (fail, fail), this eliminates (pass, pass)
the one we want is (pass, fail)
The probability of this with no other evidence is 0.42, as you calculated
With the evidence, it becomes 0.420.42+0.3(0.2)+0.3(0.8)=0.420.42+0.3=0.583333\frac{0.42}{0.42 + 0.3(0.2) + 0.3(0.8)} = \frac{0.42}{0.42 + 0.3} = 0.583333
(edited 9 years ago)
Reply 2
Original post by morgan8002
If he fails overall, there are three options, (pass, fail), (fail, pass), (fail, fail), this eliminates (pass, pass)
the one we want is (pass, fail)
The probability of this with no other evidence is 0.42, as you calculated
With the evidence, it becomes 0.420.42+0.3(0.2)+0.3(0.8)=0.420.42+0.3=0.583333\frac{0.42}{0.42 + 0.3(0.2) + 0.3(0.8)} = \frac{0.42}{0.42 + 0.3} = 0.583333



ok so how do you do this one?
Original post by JJ Downey
ok so how do you do this one?

are you familiar with Bayesian probability?
P(SW)=P(WS)P(S)P(W)P(S|W') = \frac{P(W'|S)P(S)}{P(W')}
P(SW)=(0.45)(0.9)10.53\therefore P(S|W') = \frac{(0.45)(0.9)}{1 - 0.53}
P(SW)=0.86(2dp)\therefore P(S|W') = 0.86(2 dp)
sorry about the wait, read loses as wins the first time
Reply 4
Original post by morgan8002
are you familiar with Bayesian probability?
P(SW)=P(WS)P(S)P(W)P(S|W') = \frac{P(W'|S)P(S)}{P(W')}
P(SW)=(0.45)(0.9)10.53\therefore P(S|W') = \frac{(0.45)(0.9)}{1 - 0.53}
P(SW)=0.86(2dp)\therefore P(S|W') = 0.86(2 dp)
sorry about the wait, read loses as wins the first time



no sorry would you be able to explain

haha ill try it :smile:
The general idea is that the numerator is the probability of the first hypothesis and the denominator is the sum of all possible hypotheses.
In the second example the main hypothesis is that the winds were strong and the alternative is that the winds were not strong.
P(W') = 1 - P(W), which you calculated in the last question

If you are confused on the notation: A' means A not happening,
so P(A') = 1 - P(A)

This is GCSE right?
(edited 9 years ago)
Are you ok with that?

Quick Reply

Latest