Open Side Menu Go to the Top
Register
5 events, exactly 1 to fail 5 events, exactly 1 to fail

02-04-2016 , 04:01 AM
Hi, if we have 5 events with probabilities of 80%, 75%, 70%, 65% and 60% to occur, what is the probability, that exactly one of those will fail? Doesn`t matter, which one fails.

It cant be as simple as 0.8*0.75*0.7*0.65*0.4, can it?

Thanks for your help!
5 events, exactly 1 to fail Quote
02-04-2016 , 04:35 AM
No, you have to go through all the cases. Call them events A, B, C, D, and E respectively.

Then prob of exactly one fails = prob(only A fails) + prob(only B fails) + prob(only C fails) + prob(only D fails) + prob(only E fails)

= .20*.75*.70*.65*.60

+ .80*.25*.70*.65*.60

+ .80*.75*.30*.65*.60

+ .80*.75*.70*.35*.60

+ .80*.75*.70*.65*.40
5 events, exactly 1 to fail Quote
02-04-2016 , 04:41 AM
What you calculated is the probability that the first four events succeed and the last fails. You have to sum to that the probability that the one that fails is the first, then the second and so on. So you have:

0.2*0.75*0.7*0.65*0.6 + 0.8*0.25*0.7*0.65*0.6 + 0.8*0.75*0.3*0.65*0.6 + 0.8*0.75*0.7*0.35*0.6 + 0.8*0.75*0.7*0.65*0.4

if I didn't make any typo. In total you get about 36.315%.

The calculation in R:

Code:
probs<-c(0.80, 0.75, 0.70, 0.65,0.60)
sum(prod(probs)/probs*(1-probs))
#[1] 0.36315
5 events, exactly 1 to fail Quote
02-04-2016 , 04:43 AM
Ops, didn't see whosnext's answer, sorry for the duplicate information.
5 events, exactly 1 to fail Quote
02-04-2016 , 05:25 AM
Thanks for the quick answers, guys! Appreciate it!
5 events, exactly 1 to fail Quote
02-04-2016 , 05:31 AM
no problemo nick, and I like the clever way you coded that in R
5 events, exactly 1 to fail Quote

      
m