deactherunner
Well-known member
- Joined
- Dec 3, 2012
- Messages
- 7,606
- Reaction score
- 1,178
Well, that's actually not true in the case. I think that jbug is asserting that we have one accusation from 36 years ago and then 35 straight years without an accusation...so the data set in his mind that looks like 1,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0. Sure, coming up with 35 straight 0s depends on how hard you look, i.e. What's the probability that some of those 0s are 1 but you just didn't detect them? We don't know, but no other accusations have come up, unlike in the Roy Moore or the Franken cases...the longer we go with out detecting another 1 the less likely that the one 1 we have is a true positive...that is not a flawed argument from a probability theory perspective. I actually just co-authored a paper on false positive detection probability in a bird banding study, in those data if we had an individual that was seen once and never seen again for 35 times, it is highly likely that that individual is dead, or that it was never really there to begin with.
How would you compare the probability of not seeing a bird that exists with not seeing an account of sexual assault that exists?