Return Styles: Pseud0ch, Terminal, Valhalla, NES, Geocities, Blue Moon.

Pages: 1-

Bayes Theorem

Name: Anonymous 2009-12-01 8:15

How would you use bayes theorem to calculate the probabilty of archer B hitting a target, given that one of them has.

Probabilities for the 3 archers:

A=0.6
B=0.3
C=0.5

Name: Anonymous 2009-12-01 9:18

I don't get it.  Why isn't the probability just 0.3?  The other results shouldn't affect B's probability.

Name: Anonymous 2009-12-01 9:34

Okay maybe it should be rephrased.

"One person has hit the target. What is the probability of that person being archer B".

The answer isnt just 0.3, that i am sure of.

Name: Anonymous 2009-12-01 9:53

without using bayes theorem i can get an estimate by doing 0.3 divided by the total. Which comes out at about 0.21 (done from memory)

Name: Anonymous 2009-12-02 23:44

say P(X) is the probability of player X hitting, n is the total number of hits

P(B|n=1) = P(n=1|B)*P(B)/P(n=1) = 1*0.3/(1-0.4*0.7*0.5) = 0.3488

dont trust this, i'm too lazy to tex and too lazy to check for mistakes

Name: Anonymous 2009-12-03 2:33

Out of 6+3+5 = 14 hits, 3 of them will be by B.  Therfoer >>4

Name: Anonymous 2009-12-04 7:16

>>4
This is just an intuitive statement of Bayes' Theorem in this context.

For events X and Y, we define P(X|Y) to be the probability of X occurring, given that Y has occurred.

Bayes': P(X|Y) = [P(Y|X)P(X)]/P(Y)

Let X be the event that B hits the target, and Y be the event that one of them hits the target.

P(X) = 0.3 as given
P(Y) = 0.6 + 0.3 + 0.5 = 1.4
P(Y|X) = P(one has hit, given that B has hit) = 1

So P(X|Y) = 0.3/1.4 = 0.214...

Name: Anonymous 2009-12-04 18:36

>>7
>> P(Y) = 0.6 + 0.3 + 0.5 = 1.4
P(Y) = 140%, you dont see anything wrong with this?

Don't change these.
Name: Email:
Entire Thread Thread List