ABSTRACT
Most statistical methods are based on theoretical distributions, described by parameters (such as mean and variance), which can be good approximations to the distribution of experimental data. This chapter presents key theoretical distributions and the characteristics of the populations involved. It also shows how to describe the distribution of experimental data. There are two classes of distributions: Discrete and continuous. Discrete distributions are used to describe data that can have only discrete values. The Poisson distribution is concerned with the number of events occurring during a given time or space interval. The exponential (or negative exponential) distribution describes a mechanism whereby the probability of failures (or events) within a time or distance interval depends directly on the number of un-failed items remaining. Frequency polygons are another convenient way to summarize the behavior of a large collection of experimental data.
