Calculate the posterior probability of the disease

571 Views Asked by At

Suppose the prior probability of the germ carrier is 10%. When in tests, germ carriers have the probability of $95\%$ to give positive results and $5\%$ to give negative; non-germ carriers have the probability of $1\%$ to give positive results and $99\%$ to give negative. Now, there is a person who passes the test three times, giving $2$ positive and $1$ negative results. The question is to calculate the probability of this person being germ carrier. The tests are independent.

My answer is:

Notate the prior probability of:

germ carrier $ P(A)=10 \% $

non-germ carrier $ P(\bar A)=90 \% $

and the event of

positive $b=1$

negative $b=0$

We list the conditional probability:

$P(b=1|A) = 95\%$

$P(b=0|A) = 5\%$

$P(b=1|\bar{A}) = 1\%$

$P(b=0|\bar{A}) = 99\%$

So, we calculate the prior probability of test results: $$P(b=1)=P(b=1|A)P(A) + P(b=1|\bar{A})P(\bar{A})=10.4\%$$ $$P(b=0)=P(b=0|A)P(A) + P(b=0|\bar{A})P(\bar{A})=89.6\%$$ Finally, we calculate the posterior by knowing the tests are independent

$$ P(A|b=1,1,0)=\frac{P(b=1,1,0|A)P(A)}{P(b=1,1,0)} = \frac{P(b=1|A)P(b=1|A)P(b=0|A)P(A)}{P(b=1)P(b=1)P(b=0)} \approx 46.56\%$$

So, did I do it right?

1

There are 1 best solutions below

1
On BEST ANSWER

Let $X$ be the 3 tests.

$P(A|X)=\frac{P(X|A)P(A)}{P(X|\bar{A})P(\bar{A})+P(X|A)P(A)}$

$=\frac{0.1\times C_3^2\times 0.95^2\times 0.05}{0.1\times C_3^2\times 0.95^2\times 0.05+0.9\times C_3^1\times0.01^2\times0.99 }$

$=0.9806$

Am I correct? I need your confirmation.