In: Statistics and Probability
Assume that a COVID-19 test can correctly diagnose 99% of non-infected people and 87% of infected people. Suppose that, in a population tested, 5% of people are infected. What is the probability that a person who tested positive is indeed infected?
D be an event of of being infected with the desease
So, P(D) = 0.05
be an event of of being non-infected with the desease.
So, P() = 1- 0.05 = 0.95
Let T be an event that the person diagnosed positive.
be an event that the person diagnosed negative
Test correctly diagnose 99% of non-infected people.
So, P( | ) =0.99
Test correctly diagnose 87% of infected people.
So, P( T | D ) =0.87
Probability that a person who tested positive is indeed infected
= P( D | T)
= P( T| D ) * P(D) / [ P( T| D ) * P(D) + P( T | ) * P( ) ] ( From Bayes' theorem)
=P( T | D) * P(D) / [ P( T| D ) * P(D) + {1- P( | )} * P( ) ]
= ( 0.87 * 0.05) / [ 0.87 * 0.05 + ( 1 - 0.99) * 0.95 ]
= 0.0435 / ( 0.0435 + 0.0095 )
=0.821
Probability that a person who tested positive is indeed infected = 0.0821
If you find my answer useful then please support me by putting thumbs-up. Thank you.