2
$\begingroup$

I have time intervals and probabilities for an event to occur in these time intervals. I want to calculate the probability of the event happening once or more during the entire period, that is to say with an event $X$, I want to know $P(X \geq 1)$ across all of the time periods specified. The probabilities can be assumed to be independent of each other.

I'll illustrate with example data:

 Time_bin     Probability
0 <= t < 1        70%
1 <= t < 2        30%
2 <= t < 3        10%
3 <= t < 4        50%
4 <= t < 5        20%

  Total:         Total:
0 <= t < 5         ?

I have been thinking about using a binomial distribution somehow, but I really don't know how I would go about that. Any pointers would be greatly appreciated.

$\endgroup$
  • $\begingroup$ Are the events/non-events in the separate time windows independent of each other? $\endgroup$ – jwimberley Dec 6 '16 at 11:55
  • $\begingroup$ Yes. An event happening in one time window does not affect the chance of it happening in another. Nor for that matter does it not happening in a time window $\endgroup$ – Cenfus Dec 6 '16 at 12:12
  • 1
    $\begingroup$ Your problem is straight-forward probability then. For two independent events, $P(A|B) = P(A) + P(B) - P(A) P(B)$. Just apply this rule to bins 0 and 1, this result 2, that result and 3, etc. $\endgroup$ – jwimberley Dec 6 '16 at 12:24
  • $\begingroup$ Man do I feel like a plonker, that's so simple. Nevertheless, I didn't see it, so thank you very much for your help. $\endgroup$ – Cenfus Dec 6 '16 at 12:50
1
$\begingroup$

@jwimberley has a perfectly good solution, however, this might be even a bit faster:

P(1+ events) = 1 - P(0 events) = $$1-\prod_{t=1}^5 (1-p_t)$$

P(1+ events) = 1 - 0.3*0.7*0.9*0.5*0.8 = 0.9244

$\endgroup$

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.