A distribution, presented in 1951 by the Swede, Gerhard Arfwedson, concerned with the case where each observation takes one of k equally likely values. Let M be the random variable denoting the number of values that do not occur in a sample of size n. The distribution of M is given byThe distribution has also been called the coupon-collecting distribution, since one application is to find the probability that a person having n randomly selected coupons (which might be cigarette cards, plastic toys from cereal packets, etc.) will have at least one of each of the k equally likely varieties.