00:02
The problem describes tsa doing a random security check on 10 people on a plane of 76 passengers, 12 of which are first class and 64 are regular class, or not first class, i guess.
00:16
And in the sample, none were first class.
00:19
And it asks if this can be represented by a binomial distribution.
00:23
And the one thing we want to think of right off the bat is that with binomial, we need to have.
00:39
Independent trials.
00:41
That is a really bad word for in trials, my bad.
00:44
Make that better.
00:46
Trials.
00:48
So this implies with replacement.
00:55
So if i'm doing like marbles, i should draw a red one and then put it back.
00:57
Because if i don't put it back, it changes the probability of drawing another red.
01:01
So if we're selecting 10 people, this problem is not, this problem, so here, this problem, we are doing without replacement.
01:12
Because if i draw someone to be checked for security, i'm not going to put them back on the plane and then pull them out to check them again.
01:19
So every time i take someone off the plane, the probability of them being first class is going to change.
01:26
Because we could, one theory, if we were going to do binomial, you would set your p to equal the number of first class over total passengers, the one way we could do it.
01:40
And then this is what p value would use if we did use binomial.
01:45
But if i take a passenger off the plane, then if he gets a probability of getting a first -class passenger, well, let's say i get, so one first class...