00:01
We have three ways to pay at a gas station.
00:03
We could pay with credit card, which we denote by the event a, debit card, which is b, and cash is c.
00:09
So we're given that the customer's choices are independent, and we have some probabilities.
00:15
The probability of paying with credit card for any some customer is 0 .5.
00:20
The probability of a debit card, oops, p of b, is 0 .2, and the probability of a cash is 0 .3.
00:30
So if we have 100 customers, so we'll say n equals 100, because that's our sample size, what are the mean and variance of the number who pay with a credit card? so since we're considering only the credit cards here, we can treat this as a binomial distribution because every customer will either fall into the credit card category or the not credit card category.
00:54
So we can say x, which is, we'll call that the random variable for the number of, of customers that pay with a credit card, it has a binomial distribution with the parameters 100 and 0 .5.
01:12
So this 0 .5 right here is the p for our binomial distribution, and that tells us that q is also 0 equal to 0 .5 because q is always 1 minus p, right? that represents the probability that someone does not pay with a credit card, and that means that they are debit or cash, 0 .3 plus 0 .2, 0 .5.
01:33
So the mean for a binomial distribution is equal to n times p.
01:43
So in this case, since our p is 0 .5, we have 100 times 0 .5, and that comes out to 50.
01:50
We expect half or 150 or 50 of the 100 customers to pay with credit card.
01:58
Now the variance, sigma squared, is given by n times p times q, which would be 100 times 0 .5 times 0 .5, and that's 25.
02:11
So even though there are multiple categories, if we only really care about whether one category is impacted or not that category, we could treat it as a binomial...