Table A: Important Discrete Distributions distribution pmf mean variance mgf Poisson e−λ λx x! λ λ e−λ+λet Binomial ` n x ´ πx(1 − π)n−x nπ nπ(1 − π) (πet + 1 − π)n Geometric(1) π(1 − π)x 1 π − 1 1 − π π2 π 1 − (1 − π)et Negative Binomial(1) ` s+x−1 x ´ πs(1 − π)x s π − s s(1 − π) π2 » π 1 − (1 − π)et –s Hypergeometric(2) ` m x ´` n k−x ´ ` m+n k ´ Nπ Nπ(1 − π) N −k N −1 Notes: (1) Some texts define the geometric and negative binomial distributions differ- ently. Here X counts the number of failures before s successes (s = 1 for the geometric random variables). Some authors prefer a random variable XT that counts the total number of trials. This is simply a shifting of the distribution by a constant (the number of successes): XT = X + s. The formulas for the pdf, mean, variance, and moment generating function of XT all follow easily from this equation. (2) For the hypergeometric distribution, the parameters are m items of the type being counted, n items of the other type, and k items selected without re- placement. We define N = m + n (total number of items) and π = m N = m m+n (proportion of items that are of the first type).
Purchased from American Mathematical Society for the exclusive use of nofirst nolast (email unknown) Copyright 2011 American Mathematical Society. Duplication prohibited. Please report unauthorized use to cust-serv@ams.org. Thank You! Your purchase supports the AMS' mission, programs, and services for the mathematical community.