
t ‐ statistic: The t-value expresses the magnitude of the difference in terms of the variation in your sample data. F‐ statistic: An F - test is any statistical test in which the test statistic has an F-distribution under the null hypothesis. The F statistic simply compares the combined effect of all variables. Thus, Chi-square test is a non‐parametric statistic. Ordinal data is sometimes used in nonparametric statistics which means it does not rely on numbers but rather on a ranking or order of sorts. The normal distribution model and the linear regression model are examples of nonparametric statistics. The model structure of nonparametric approaches is determined from data rather than being established a priori. Certain descriptive statistics, statistical models, inference, and statistical tests are examples of nonparametric statistics. Like all non-parametric statistics, the Chi-square is robust with respect to the distribution of the data.
The Chi-square statistic is a non-parametric (distribution free) tool designed to analyze group differences when the dependent variable is measured at a nominal level.
The nonparametric approach is a statistical method that makes no assumptions about the sample's characteristics (its parameters) or whether the observed data is quantitative or qualitative.