Suppose that the time (in hours) required to repair a machine is an exponentially distributed random variable with parameter $\lambda = 0.2$. What is:

(a) the probability that a repair time exceeds 10 hours?
(b) the conditional probability that a repair takes at least 7 hours, given that it takes more than 6 hours?

I was able to answer part (a). The survival function of the exponential distribution is $e^{-\lambda t}$ so I plugged in for $\lambda = 0.2$ and $t = 10$ to calculate the probability that repair time is greater than $2$. I got $e^{-0.2\times 10} = .13533$ which is correct.

For part (b), I know I have to use the standard rules of conditional probability: $$ P(X > 7 | X > 6) = \frac{P(X > 7 \cap X > 6)}{P(X > 6)} $$ but for some reason my answer is incorrect.

Am I doing this incorrectly?


My guess is you have a cancellation error -- your approach seems correct.

The exponential random variable has the "memoryless property": given that we have seen no event up to time $t$, the conditional distribution of the remaining time until the event is the same as it originally was.

As you noted, if $X$ is the time until the first event, and we have times $t$ and $t + s$ (with $s \geq 0$), we have \begin{equation*}\begin{split} P(X > t + s | X > t) &= \frac{P(X > t + s)}{P(X > t)} \\ &= \frac{e^{-\lambda(t + s)}}{e^{-\lambda t}} \\ &= e^{-\lambda s} \\ &= P(X > s). \end{split}\end{equation*}


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.