Example 1
Question: A company has three plants P, Q, and R manufacturing the same product. Plant P produces 50% of the total output, plant Q produces 30%, and plant R produces the remaining 20%. It is known that 3% of items from plant P, 4% of items from plant Q, and 5% of items from plant R are defective. One item is selected at random from the combined stockpile and is found to be defective. Find the probability that the defective item was produced by plant Q.
Solution: Let \( E_1, E_2, E_3 \) be the events that the selected item was produced by plants P, Q, and R respectively, and let \( A \) be the event that the selected item is defective. The prior probabilities are: \[P(E_1) = 0.50, \quad P(E_2) = 0.30, \quad P(E_3) = 0.20\] The conditional probabilities (likelihoods) of a defective item from each plant are: \[P(A \mid E_1) = 0.03, \quad P(A \mid E_2) = 0.04, \quad P(A \mid E_3) = 0.05\] By the Total Probability Theorem, the probability that any randomly chosen item is defective: \[P(A) = P(E_1)\cdot P(A \mid E_1) + P(E_2)\cdot P(A \mid E_2) + P(E_3)\cdot P(A \mid E_3)\] \[P(A) = (0.50)(0.03) + (0.30)(0.04) + (0.20)(0.05)\] \[P(A) = 0.015 + 0.012 + 0.010 = 0.037\] By Bayes' Theorem, the probability that the defective item came from plant Q is: \[P(E_2 \mid A) = \frac{P(E_2)\cdot P(A \mid E_2)}{P(A)}\] \[P(E_2 \mid A) = \frac{(0.30)(0.04)}{0.037} = \frac{0.012}{0.037}\] \[P(E_2 \mid A) = \frac{12}{37}\]
Answer: \(\dfrac{12}{37}\)
Example 2
Question: In a large hospital, 70% of the patients in a particular ward are adults and 30% are children. Among adults, the probability of testing positive for a certain condition is 0.08, while among children it is 0.05. A randomly selected patient from the ward tests positive. What is the probability that this patient is a child?
Solution: Let \( E_1 \) be the event that the selected patient is an adult, \( E_2 \) be the event that the selected patient is a child, and \( A \) be the event that the patient tests positive. The prior probabilities are: \[P(E_1) = 0.70, \quad P(E_2) = 0.30\] The conditional probabilities of testing positive are: \[P(A \mid E_1) = 0.08, \quad P(A \mid E_2) = 0.05\] By the Total Probability Theorem: \[P(A) = P(E_1)\cdot P(A \mid E_1) + P(E_2)\cdot P(A \mid E_2)\] \[P(A) = (0.70)(0.08) + (0.30)(0.05)\] \[P(A) = 0.056 + 0.015 = 0.071\] By Bayes' Theorem, the probability that the positive patient is a child: \[P(E_2 \mid A) = \frac{P(E_2)\cdot P(A \mid E_2)}{P(A)}\] \[P(E_2 \mid A) = \frac{(0.30)(0.05)}{0.071} = \frac{0.015}{0.071}\] \[P(E_2 \mid A) = \frac{15}{71}\]
Answer: \(\dfrac{15}{71}\)