what is the probability that drug was effective for this person knowing the Poisson distribution of the number of time that person get sick

995 Views Asked by At

The number of colds person gets in a year has ${\rm Poisson}(3)$ distribution. A new drug lower it to ${\rm Poisson}(.75)$ and is effective for $8$ out of $10$ people. The entire population was given the drug. One person was selected at random from the population and was found to have $1$ cold during the year. What is the probability that the drug was effective for this person?

Assuming $A$ is having $1$ cold per year and $B$ the drug is effective.

By knowing $P(B) = 8/10$ and finding the probability of having 1 cold/year before and after the drug. $P(A|B) = \exp(-.75)(.75)=.354275$ and $P(A|B^{c}) = exp(-3)(3)= .14936$, I can almost use the Bayes' theorem to find the $P(B|A)$ which is the probability the drug being effective knowing the person have been chosen had only 1 cold.

$P(B|A) = \frac{P(A|B)P(B)}{P(A|B)P(B)+P(A|B^{c})P(B^{c})}$.

I still miss a part of the equation $P(B^{c})$ if my assumption was correct.

1

There are 1 best solutions below

6
On BEST ANSWER

The mistake is in $$P(A\mid B^c)=\exp(-3)3=0.149\neq 0.22245$$ as you have it. So this is only a calculation mistake, rest including $P(B^c)=0.2$, is correct. To see this note that there are only two outcomes (as defined):

  1. $B:$ the drug is effective,
  2. $C:$ the drug is not effective.

These are by their definition complementary. $B$ occurs or $C$ occurs. So, it must be that $P(B)=1-P(C)$ (actually $C$ stands for $B^c$ here).