MULTINOMIAL DISTRIBUTION

A multinomial ditribution is simply a generalization of the binomial distribution. In a binomial distribution, we are given the probability of the number of "successes" and "failures" in n (a random number) independent trials of a two outcome process. The fixed probabilities p and q=1-p, gives us the probability of success and failure in any one trial. Thus, the multinomial distribution gives the probability of each combination of the outcomes in n (a random number) independent trials of a k outcome process. Also, a multinomial distribution is a discrete distribution (i.e. its outcomes are discrete). For example, if one threw a dice 60 times, each outcome would be a mutually exclusive outcome (i.e. 1 or 3 or 6). In all, when it comes to a multinomial distribution, individual trials are independent and the outcomes are mutually exclusive and all inclusive.

-Tamara Nelson