Example 1
Question: A company produces light bulbs using three machines \( M_1 \), \( M_2 \), and \( M_3 \). Machine \( M_1 \) produces \( 30\% \) of the total bulbs, \( M_2 \) produces \( 45\% \), and \( M_3 \) produces \( 25\% \). The probability that a bulb produced by \( M_1 \), \( M_2 \), and \( M_3 \) is defective are \( 0.04 \), \( 0.02 \), and \( 0.05 \) respectively. A bulb is picked at random and found to be defective. Find the probability that it was produced by machine \( M_2 \).
Solution: Let \( M_1 \), \( M_2 \), \( M_3 \) be the events that a bulb is produced by the respective machines, and let \( D \) be the event that the bulb is defective. The prior probabilities are: \[ P(M_1) = 0.30, \quad P(M_2) = 0.45, \quad P(M_3) = 0.25 \] The conditional probabilities of a defective bulb from each machine are: \[ P(D \mid M_1) = 0.04, \quad P(D \mid M_2) = 0.02, \quad P(D \mid M_3) = 0.05 \] Using the Total Probability Theorem, we find \( P(D) \): \[ P(D) = P(M_1) \cdot P(D \mid M_1) + P(M_2) \cdot P(D \mid M_2) + P(M_3) \cdot P(D \mid M_3) \] \[ P(D) = (0.30)(0.04) + (0.45)(0.02) + (0.25)(0.05) \] \[ P(D) = 0.012 + 0.009 + 0.0125 \] \[ P(D) = 0.0335 \] Now, applying Bayes' Theorem to find \( P(M_2 \mid D) \): \[ P(M_2 \mid D) = \frac{P(M_2) \cdot P(D \mid M_2)}{P(D)} \] \[ P(M_2 \mid D) = \frac{(0.45)(0.02)}{0.0335} \] \[ P(M_2 \mid D) = \frac{0.009}{0.0335} \] \[ P(M_2 \mid D) = \frac{9}{33.5} = \frac{18}{67} \]
Answer: \( P(M_2 \mid D) = \dfrac{18}{67} \)
Example 2
Question: In a city, there are three courier services \( C_1 \), \( C_2 \), and \( C_3 \). A logistics company sends \( 20\% \) of its parcels through \( C_1 \), \( 50\% \) through \( C_2 \), and \( 30\% \) through \( C_3 \). The probabilities that a parcel is delivered late by \( C_1 \), \( C_2 \), and \( C_3 \) are \( 0.06 \), \( 0.03 \), and \( 0.08 \) respectively. A parcel is found to have been delivered late. Find the probability that it was sent through \( C_3 \).
Solution: Let \( C_1 \), \( C_2 \), \( C_3 \) be the events that a parcel is sent through the respective courier service, and let \( L \) be the event that the parcel is delivered late. The prior probabilities are: \[ P(C_1) = 0.20, \quad P(C_2) = 0.50, \quad P(C_3) = 0.30 \] The conditional probabilities of late delivery from each service are: \[ P(L \mid C_1) = 0.06, \quad P(L \mid C_2) = 0.03, \quad P(L \mid C_3) = 0.08 \] Using the Total Probability Theorem, we find \( P(L) \): \[ P(L) = P(C_1) \cdot P(L \mid C_1) + P(C_2) \cdot P(L \mid C_2) + P(C_3) \cdot P(L \mid C_3) \] \[ P(L) = (0.20)(0.06) + (0.50)(0.03) + (0.30)(0.08) \] \[ P(L) = 0.012 + 0.015 + 0.024 \] \[ P(L) = 0.051 \] Now, applying Bayes' Theorem to find \( P(C_3 \mid L) \): \[ P(C_3 \mid L) = \frac{P(C_3) \cdot P(L \mid C_3)}{P(L)} \] \[ P(C_3 \mid L) = \frac{(0.30)(0.08)}{0.051} \] \[ P(C_3 \mid L) = \frac{0.024}{0.051} \] \[ P(C_3 \mid L) = \frac{24}{51} = \frac{8}{17} \]
Answer: \( P(C_3 \mid L) = \dfrac{8}{17} \)