Choosing Between Parametric and Non-parametric Tests in Statistical Data Analysis

In this chapter, the authors describe what is the parametricParametric and non-parametricNon-parametric tests in statistical data analysisStatistical data analysis and the best scenarios for the use of each test. It provides a guide for the readers on how to choose which of the test is most suitable for their specific research, including a description of the differences, advantages, and disadvantages of using the two types of tests. Before using the different statistical methodsStatistical Methods in R (see Chap. 6 ), the users need to understand the differences and conditions under which the various tests or methods are applied. The term “parametricParametric” is used to refer to parametersParameters of the resultant datasets (distribution) that supposedly assume that the sample (mean, standard deviations, etc.) is normally distributed. While the “non-parametricNon-parametric” tests (usually measured in median) are referred to as “distribution-freeDistribution-free” tests given the fact that the supporting methods assume that the analyzed datasets follow a certain but not specified distribution. Thus, the different statistical procedures or supporting methods (parametricParametric versus non-parametricNon-parametric) are followed based on the type of the available dataset (nominal, ordinal, continuous, discreteDiscrete) and/or the number of the independentIndependent versus dependentDependent groups or categories of the variablesVariables which are described in Chapter 5 .