A manufacturing process produces integrated circuit chips. Over the long run the fraction of bad chips produced by the process is around 20%. Thoroughly testing a chip to determine whether it is good or bad is rather expensive, so a cheap test is tried. All good chips will pass the cheap test, but so will 10% of the bad chips.
Given that a chip passes the test, what is the probability that the chip was defective?

P(T)= probability that the chip is not defective * probability that it passes the test given that is not defective + probability that the chip is defective * probability that it passes the test given that is defective = 0.80 * 1 + 0.20 * 0.10 = 0.82

for conditional probability we can use the theorem of Bayes. If we define the event D=the chip was defective , then

P(D/T)=P(D∩T)/P(T) = 0.20 * 0.10/0.82= 0.0244 (2.44%)

where

P(D∩T)=probability that the chip is defective and passes the test

P(D/T)=probability that the chip is defective given that it passes the test