Robust Analysis with Little Data
Nonparametric tests are statistical procedures which can be used to make successful inferences when there is little available data. Nonparametric tests are designed for small data sets and make far fewer assumptions about the data. This is especially useful for data sets where the distribution of the data may not be clear. In most cases, the nonparametric tests are often much easier to apply and provide clearer interpretation than traditional parametric tests.

What are Nonparametric Tests?
Nonparametric tests are an alternative to many of the widely known parametric hypothesis tests. Nonparametric tests are more robust than parametric hypothesis tests in the sense they do not always need the parametric assumptions such as normality or generalized assumptions regarding the underlying distribution.

Nonparametric Assumptions
Nonparametric tests are unique because they do not rely on the estimation of parameters such as mean or variance like their parametric counterparts. The nonparametric tests are based on very general conditions and almost always have no parameters regarding the specific shape or type of distribution. The most universal assumptions for a nonparametric test are that:
the observations are independent, and
the variable in question has underlying continuity.
These conditions are far weaker then the traditional parametric test. They also can be applied in areas where parametric tests cannot. For instance, the data for nonparametric tests are not restricted to interval scale data; they can include ordinal and other data in a nominal or categorical scale. Therefore, they can be described as parameter-free or distribution-free procedures.

Included Tests
The three tests included with StatTools Nonparametric Analysis Pack are:

The Sign Test
Wilcoxon-Signed Rank Test
Mann-Whitney Test (also known as Wilcoxon Rank-Sum Test)

StatTools Nonparametric Analysis Pack: PAL# 1320, $99