Parametric and Non-Parametric Data
By: Jon • Research Paper • 499 Words • April 14, 2010 • 1,649 Views
Parametric and Non-Parametric Data
Parametric and Nonparametric Data Identification
It is not always easy deciding whether data should be treated as parametric or nonparametric. A parametric test is a test that requires a parametric assumption, such as normality. A nonparametric test does not rely on parametric assumptions like normality (Simon, 2005). Whichever test a researcher decides to use, one must have a basic understanding of both parametric and nonparametric data.
Parametric data is data that can be measured. For example, heights, weight, depth, amount of money, square footage are all forms of parametric data. These are all data with parameters. Interval and ratio measurements are considered parametric.
Data is considered parametric if it has the following three assumptions: normality, equal variances, and independence. First, is the data obtained from a population that is considered normal? Second, the populations from which the data is obtained should have equal variances. The F-test can be used to test the hypothesis that the samples have been drawn from populations with the equal variances. And, third, the data should be measured on an interval scale (Eachus, 2000).
Nonparametric data, on the other hand, does not have parameters and allows one to analyze data without assumptions. Specifically, nonparametric methods were developed to be used in cases when the researcher knows nothing about the parameters of the variable of interesting the population (Statsoft, Inc., 1984-2003). Nonparametric data does not rely on parameters.
Nonparametric data uses qualitative methods as opposed to quantitative methods. In sample studies, qualitative methods are more concerned with the experiences of the participants rather than numbers associated with parametric data. In recent years, particularly in the health sciences, qualitative methods have become increasingly popular among researchers (Eachus, 2000).
In many cases during research, one does not know if the data is drawn from a normally distributed population. For example, the number of car accidents or rates of rare diseases