Example 1
Question: Three factories \( F_1, F_2, F_3 \) manufacture a particular electronic component. Factory \( F_1 \) produces \( 30\% \) of the total output, \( F_2 \) produces \( 45\% \), and \( F_3 \) produces \( 25\% \). The probabilities that a component produced by \( F_1, F_2, F_3 \) is defective are \( 0.02,\ 0.03, \) and \( 0.05 \) respectively. A component is chosen at random and is found to be defective. Find the probability that it was manufactured by factory \( F_3 \).
Solution: Let \( E_1, E_2, E_3 \) be the events that the component came from factory \( F_1, F_2, F_3 \) respectively, and let \( D \) be the event that the component is defective. The prior probabilities are: \[ P(E_1) = 0.30, \quad P(E_2) = 0.45, \quad P(E_3) = 0.25 \] The conditional probabilities of a defective component from each factory are: \[ P(D \mid E_1) = 0.02, \quad P(D \mid E_2) = 0.03, \quad P(D \mid E_3) = 0.05 \] Using the Total Probability Theorem, the total probability of getting a defective component is: \[ P(D) = P(E_1) \cdot P(D \mid E_1) + P(E_2) \cdot P(D \mid E_2) + P(E_3) \cdot P(D \mid E_3) \] \[ P(D) = (0.30)(0.02) + (0.45)(0.03) + (0.25)(0.05) \] \[ P(D) = 0.006 + 0.0135 + 0.0125 \] \[ P(D) = 0.032 \] By Bayes' Theorem, the probability that the defective component came from \( F_3 \) is: \[ P(E_3 \mid D) = \frac{P(E_3) \cdot P(D \mid E_3)}{P(D)} \] \[ P(E_3 \mid D) = \frac{(0.25)(0.05)}{0.032} \] \[ P(E_3 \mid D) = \frac{0.0125}{0.032} \] \[ P(E_3 \mid D) = \frac{125}{320} = \frac{25}{64} \]
Answer: \( P(E_3 \mid D) = \dfrac{25}{64} \)
Example 2
Question: In a city, three medical clinics \( C_1, C_2, C_3 \) administer flu shots. Clinic \( C_1 \) administers \( 20\% \) of all flu shots, \( C_2 \) administers \( 50\% \), and \( C_3 \) administers \( 30\% \). The probabilities that a person who received a flu shot from \( C_1, C_2, C_3 \) develops flu despite vaccination are \( 0.08,\ 0.06, \) and \( 0.04 \) respectively. A vaccinated person is selected at random and is found NOT to have developed flu. Find the probability that the person received the shot from clinic \( C_2 \).
Solution: Let \( H_1, H_2, H_3 \) be the events that the person was vaccinated at clinic \( C_1, C_2, C_3 \) respectively, and let \( \overline{F} \) be the event that the person did NOT develop flu. The prior probabilities are: \[ P(H_1) = 0.20, \quad P(H_2) = 0.50, \quad P(H_3) = 0.30 \] The probabilities of developing flu from each clinic: \[ P(F \mid H_1) = 0.08, \quad P(F \mid H_2) = 0.06, \quad P(F \mid H_3) = 0.04 \] So the probabilities of NOT developing flu from each clinic are: \[ P(\overline{F} \mid H_1) = 1 - 0.08 = 0.92 \] \[ P(\overline{F} \mid H_2) = 1 - 0.06 = 0.94 \] \[ P(\overline{F} \mid H_3) = 1 - 0.04 = 0.96 \] Using the Total Probability Theorem: \[ P(\overline{F}) = P(H_1) \cdot P(\overline{F} \mid H_1) + P(H_2) \cdot P(\overline{F} \mid H_2) + P(H_3) \cdot P(\overline{F} \mid H_3) \] \[ P(\overline{F}) = (0.20)(0.92) + (0.50)(0.94) + (0.30)(0.96) \] \[ P(\overline{F}) = 0.184 + 0.470 + 0.288 \] \[ P(\overline{F}) = 0.942 \] By Bayes' Theorem, the probability that the person came from clinic \( C_2 \) given they did not develop flu: \[ P(H_2 \mid \overline{F}) = \frac{P(H_2) \cdot P(\overline{F} \mid H_2)}{P(\overline{F})} \] \[ P(H_2 \mid \overline{F}) = \frac{(0.50)(0.94)}{0.942} \] \[ P(H_2 \mid \overline{F}) = \frac{0.470}{0.942} \] \[ P(H_2 \mid \overline{F}) = \frac{470}{942} = \frac{235}{471} \]
Answer: \( P(H_2 \mid \overline{F}) = \dfrac{235}{471} \)