Suppose that the expected number of deaths due to bladder cancer for all workers at a tire plant on January 1, 1964, over the next 20 years (1/1/64-12/31/83) based on US mortality rates is 1.8. If the Poisson distribution is assumed to hold and there are 6 reported deaths due to bladder cancer among the tire workers, then how unusual is this event?

Solution

Let $X$ denote the number of deaths due bladder cancer over 20 year period 1/1/64-12/31/83.

Given that $E(X) = \lambda = 1.8$. $X\sim Po(1.8)$.

The pmf of Poisson distribution with $\lambda =1.8$ is

$$
\begin{aligned}
P(X=x) &= \frac{e^{-1.8}(1.8)^x}{x!},\
&\quad x=0,1,2,\cdots
\end{aligned}
$$

The probability that there are $6$ deaths due to bladder cancer among the tire workers is

$$ \begin{aligned} P(X=6) &= \frac{e^{-1.8}1.8^{6}}{6!}\\ &= 0.00781 \end{aligned} $$

As the $P(X=6) = 0.00781$ is very close to zero, it is an unusual event.

Further Reading