Nonparametric Methods in Statistics with SAS Applications

Chapter 1

Hypotheses Testing for Two Samples

Generally speaking, statistical methodology is split into two broad classes: paramet-

ric and nonparametric. Parametric methods assume that forms of distributions of

random variables are known and only a fixed number of parameters of these distri-

butions must be estimated. In many applications of parametric methods, even if the

exact form of the distribution is not known, observations come from a sufficiently

large sample, thus the use of the normal approximation is validated by the Central

Limit Theorem. In the situations when the sample size is relatively small and no con-

jecture may be made regarding