Question

How does a nonparametic test different from a parametic test?

Answer 1

A parametric test contains certain statistical assumptions about the distributions of data. These tests assume that the sample data comes from a population that follows a probability distribution based on a fixed set of parameters. In these tests model structure is specified apriori. Parametric tests give more accurate results than non-parametric tests when all the statistical assumptions are valid. Examples of a parametric test would be 1-sample and 2-sample tests.

A non parametric test do not rely on any distribution and are more robust than parametric tests. i.e they cover larger variety of scenarios.Even if non-parametric tests have a specified distribution, then its parameters are not specified. The model structure is determined using the data. Examples of non-parametric test would be Mann-Whitney test and Friedman test.