ABSTRACT
Since the categories are mutually exclusive and exhaustive, we have Σπi=1 and Σni=n. Thus, it can be shown that the probability mass function (called the multinomial distribution) for n=(n1, n2, …, nk) with Π as defined above is given by:
(3.1)
where πi>0, Σπi=1 and Thus n is a random vector which can take on any value for which
(i) 0≤ni≤n for i=1, 2, …, k, and (ii) Σni=n.
