A Positive Test for a Rare Disease
The puzzle
A disease affects 1 person in 100. A test for it detects the disease in 99% of people who have it, and wrongly reports it in 5% of people who do not.
You take the test and it comes back positive. What is the probability that you actually have the disease?
Stuck?
One at a time, smallest first. Open only as many as you need — the whole point of the puzzle is the part you work out yourself.
Hint 1
Imagine 10,000 people taking the test. How many true positives, and how many false ones?
Hint 2
The false positives come from a much larger pool than the true positives do.
Show the answer Hide the answer
About 17% - one chance in six. The test being "99% accurate" does not make a positive result 99% reliable.
How to get there
Take 10,000 people. 100 have the disease and the test catches 99 of them. The other 9,900 are healthy, and 5% of them - 495 people - test positive anyway.
So 99 + 495 = 594 people test positive, and only 99 of them are ill: 99/594 = 1/6, about 16.7%.
The false positives outnumber the true ones five to one because they are drawn from a pool ninety-nine times larger. This is the base rate fallacy, and it is why screening a whole population for something rare produces mostly false alarms - and why a positive screening result is normally followed by a second, different test rather than a diagnosis.
The technique worth keeping
Do not reason with percentages; reason with a population. Writing out the four counts - true positive, false positive, true negative, false negative - turns Bayes' theorem into arithmetic you cannot get backwards.