00:01
Okay, so in any given population, if a population has a certain proportion p, like in this case, right? when you take a sample, you'll get a p hat, and every time you take a sample, you'll get a different p hat.
00:16
Right.
00:16
And so when you take all the different samples that you could possibly take from that population, and you put them in a distribution, that is called a sampling distribution of p hat.
00:31
Okay? now, if you are trying to figure out the shape of this distribution, because of the central limit theorem, we know that when n is large, that means that the sampling distribution will be approximately normal or symmetrical.
00:59
Now, different classes use different metrics for deciding what is large enough, so some classes just say like if n is greater than 30 or 40.
01:09
Others look at n times p and n times 1 minus p and see if those are greater than 5 or 10.
01:15
So you'll have to see whatever your specific class uses and see if n is large enough based on that.
01:23
But usually n is 40 is probably going to be okay.
01:29
But at the same time, it really just depends on whatever your class is using...