In: Statistics and Probability
An urn contains 4 marbles, either blue or green. The number of blue marbles is equally likely to be 0, 1, 2, 3, or 4. Suppose we do 3 random draws with replacement, and the observed sequence is: blue, green, blue. What is the probability the urn contains just 1 blue marble?
B0 = Event of urn contains 0 blue marbles
B1 = Event of urn contains 1 blue marbles
B2 = Event of urn contains 2 blue marbles
B3 = Event of urn contains 3 blue marbles
B4 = Event of urn contains 4 blue marbles
The number of blue marbles is equally likely to be 0, 1, 2, 3, or 4.
Therefore,
P(B0)=P(B1)=P(B2)=P(B3)=P(B4) = 1/5 =0.2
X : Event of drawing blue, green, blue in sequence with replacement
P(X|B0) = Probability drawing blue, green, blue in sequence with replacement = 0 (as there are no blue marbels in the urn)
P(X|B1) : (1/4)x(3/4)x(1/4) = 3/64 (As there are 1 blue marble and 3 green marbles; Probability of drawing a blue marble each time is 1/4 and green marbles is 3/4 as the draw with replacement)
Similary
P(X|B2) = (2/4)x(2/4)x(2/4) = 8/64
P(X|B3) = (3/4)x(1/4)x(3/4) = 9/64
P(X|B4) = 0 (as when the urn contains all blue marbles, number of green marbles = 0, so we can not draw green marble in the second draw)
Suppose we do 3 random draws with replacement, and the observed sequence is: blue, green, blue, probability the urn contains just 1 blue marble = P(B1|X)
By Bayes theorem,
P(B1)P(X|B1) = (1/5) x (3/64) = 3/320
P(B0)P(X|B0) = 0
P(B2)P(X|B2) = (1/5) x (8/64) = 8/320
P(B3)P(X|B3) = (1/5) x (9/64) = 9/320
P(B4)P(X|B4) = 0
P(B0)P(X|B0) + P(B1)P(X|B1) + P(B2)P(X|B2) + P(B3)P(X|B3) + P(B4)P(X|B4) = 0+3/320+8/320+9/320+0 = 20/320
Suppose we do 3 random draws with replacement, and the observed sequence is: blue, green, blue, probability the urn contains just 1 blue marble = 3/20 = 0.15