Example 1
Question: A factory has four machines M1, M2, M3, and M4 that produce light bulbs. Each machine produces 25% of the total output. The probability that a bulb produced is defective is 5% for M1, 3% for M2, 8% for M3, and 2% for M4. A bulb is picked at random and found to be defective. Find the probability that it was produced by machine M3.
Solution: Let the events be defined as follows. Let \( M_1, M_2, M_3, M_4 \) be the events that a randomly selected bulb was produced by machine M1, M2, M3, M4 respectively. Let \( D \) be the event that the selected bulb is defective. Given prior probabilities: \[ P(M_1) = P(M_2) = P(M_3) = P(M_4) = \frac{1}{4} = 0.25 \] Conditional probabilities of a defective bulb from each machine: \[ P(D \mid M_1) = 0.05, \quad P(D \mid M_2) = 0.03, \quad P(D \mid M_3) = 0.08, \quad P(D \mid M_4) = 0.02 \] First, find the total probability of picking a defective bulb using the Law of Total Probability: \[ P(D) = P(M_1)\cdot P(D \mid M_1) + P(M_2)\cdot P(D \mid M_2) + P(M_3)\cdot P(D \mid M_3) + P(M_4)\cdot P(D \mid M_4) \] Substituting the values: \[ P(D) = 0.25 \times 0.05 + 0.25 \times 0.03 + 0.25 \times 0.08 + 0.25 \times 0.02 \] \[ P(D) = 0.25 \times (0.05 + 0.03 + 0.08 + 0.02) \] \[ P(D) = 0.25 \times 0.18 = 0.045 \] Now, applying Bayes' Theorem to find \( P(M_3 \mid D) \): \[ P(M_3 \mid D) = \frac{P(M_3) \cdot P(D \mid M_3)}{P(D)} \] \[ P(M_3 \mid D) = \frac{0.25 \times 0.08}{0.045} \] \[ P(M_3 \mid D) = \frac{0.02}{0.045} = \frac{20}{45} = \frac{4}{9} \]
Answer: \( P(M_3 \mid D) = \dfrac{4}{9} \)
Example 2
Question: A medical test is conducted on patients in a hospital. Based on lifestyle categories, patients are equally likely to fall into one of four groups: Group A (sedentary, smoker), Group B (sedentary, non-smoker), Group C (active, smoker), Group D (active, non-smoker). The probability that a patient from each group tests positive for a certain condition is 30% for Group A, 20% for Group B, 15% for Group C, and 10% for Group D. A randomly selected patient tests positive. Find the probability that this patient belongs to Group A.
Solution: Let \( A, B, C, D \) represent the events that a randomly selected patient belongs to Group A, Group B, Group C, or Group D respectively. Let \( T \) be the event that the patient tests positive. Given prior probabilities: \[ P(A) = P(B) = P(C) = P(D) = \frac{1}{4} \] Conditional probabilities of testing positive: \[ P(T \mid A) = 0.30, \quad P(T \mid B) = 0.20, \quad P(T \mid C) = 0.15, \quad P(T \mid D) = 0.10 \] First, find the total probability of a positive test using the Law of Total Probability: \[ P(T) = P(A)\cdot P(T \mid A) + P(B)\cdot P(T \mid B) + P(C)\cdot P(T \mid C) + P(D)\cdot P(T \mid D) \] \[ P(T) = \frac{1}{4}(0.30 + 0.20 + 0.15 + 0.10) \] \[ P(T) = \frac{1}{4} \times 0.75 = \frac{0.75}{4} = \frac{3}{16} \] Now, applying Bayes' Theorem to find \( P(A \mid T) \): \[ P(A \mid T) = \frac{P(A) \cdot P(T \mid A)}{P(T)} \] \[ P(A \mid T) = \frac{\dfrac{1}{4} \times 0.30}{\dfrac{3}{16}} \] \[ P(A \mid T) = \frac{\dfrac{0.30}{4}}{\dfrac{3}{16}} = \frac{0.30}{4} \times \frac{16}{3} \] \[ P(A \mid T) = \frac{0.30 \times 16}{4 \times 3} = \frac{4.8}{12} = \frac{2}{5} \]
Answer: \( P(A \mid T) = \dfrac{2}{5} \)