Detailed Explanation
This problem is solved using Bayes' theorem, which lets us reverse a conditional probability. We are told how the test behaves given the disease status (like the accuracy of the test), but we want the opposite: the disease status given the test result. Let \( E_1 \) be the event that a person has the disease and \( E_2 \) that a person does not have the disease. Let \( A \) be the event that the test result is positive. We know the prior probabilities \( P(E_1) \) and \( P(E_2) \), and the conditional probabilities \( P(A \mid E_1) \) (true positive) and \( P(A \mid E_2) \) (false positive). Bayes' theorem then gives us \( P(E_1 \mid A) \), the probability of actually having the disease when the test is positive.
Formula Used
\[ P(E_1 \mid A) = \frac{P(E_1)\, P(A \mid E_1)}{P(E_1)\, P(A \mid E_1) + P(E_2)\, P(A \mid E_2)} \]
Solution
- Step 1: Define the events. Let \( E_1 \) = the person has the disease, and \( E_2 \) = the person does not have the disease. Let \( A \) = the test result is positive. Since only 0.1 percent of the population has the disease, we get \( P(E_1) = \dfrac{0.1}{100} = 0.001 \) and \( P(E_2) = 1 - 0.001 = 0.999 \).
- Step 2: Write the conditional probabilities. The test is 99 percent effective when the disease is present, so \( P(A \mid E_1) = 0.99 \). The test gives a false positive for 0.5 percent of healthy people, so \( P(A \mid E_2) = 0.005 \).
- Step 3: We need \( P(E_1 \mid A) \), the probability of having the disease given a positive test. By Bayes' theorem: \[ P(E_1 \mid A) = \frac{P(E_1)\, P(A \mid E_1)}{P(E_1)\, P(A \mid E_1) + P(E_2)\, P(A \mid E_2)} \]
- Step 4: Substitute the values into the formula: \[ P(E_1 \mid A) = \frac{0.001 \times 0.99}{0.001 \times 0.99 + 0.999 \times 0.005} \]
- Step 5: Compute each product. The numerator is \( 0.001 \times 0.99 = 0.00099 \). In the denominator, \( 0.999 \times 0.005 = 0.004995 \), so the denominator is \( 0.00099 + 0.004995 = 0.005985 \).
- Step 6: Divide to get the final probability: \[ P(E_1 \mid A) = \frac{0.00099}{0.005985} = \frac{990}{5985} = \frac{22}{133} \approx 0.1654 \]
Final Answer
The probability that the person actually has the disease given a positive test result is \( \dfrac{22}{133} \approx 0.1654 \), that is, about 16.5 percent.
Common Mistake
A very common error is to think the answer must be close to 0.99 because the test is 99 percent effective. This confuses \( P(A \mid E_1) \) with \( P(E_1 \mid A) \). Because the disease is rare, most positive results actually come from false positives among the large healthy population, which is why the true probability is only about 16.5 percent.