Parametric Tests

Abstract

Inferential statistics help researchers by two major means. Firstly, they are used to extrapolate the result obtained from studying sample to a greater population. Secondly, they are used for hypothesis testing. They are otherwise called as statistical test of significance. These tests are broadly classified into parametric and non-parametric tests of significance. Parametric tests are those that make assumptions about the parameters of the population. The general assumption is that the population data are normally distributed. Hence, the sample data that is collected from population also to be normally distributed in order to apply the parametric test of significance to test hypothesis. Apart from that, there are various other assumptions to be fulfilled by the sample data to use parametric test of significance. If any of these assumptions is violated, then its equivalent non-parametric tests have to be applied. The appropriate choice of selection of parametric test depends on, type of dependent and independent variables, number of groups to be compared and the relatedness of data. Various parametric tests commonly used are, student’s t test, paired t test, one way and two ways ANOVA, one way and two way repeated measures ANOVA, Pearson’s correlation and linear regression.