In: Math
Please do not use this as an example: For example, let’s say you had four groups, representing drugs A B C D, with each group composed of 20 people in each group and you’re measuring people’s cholesterol level.
In your own words, describe the difference between Among Group Variation and Within Group Variation. Discuss how you would evaluate the variation and other methods to ensure that the data is appropriate to use for the test. Illustrate using a specific example.
Suppose there are 3 classrooms in a school, say A,B,C and our goal is to analyse if there is a difference in performance of students in the 3 classrooms. Here, the among group variation will be the difference in performance of students in the same classroom and the between group variation will be the difference in performance of students in different classrooms. The null hypothesis is that there is no significant difference performance of students in different classrooms and the alternative being there is a difference.This is tested using ANOVA.
Before carrying out ANOVA we test for the assumption of normality using Kruskal Wallis test or the boxplot which should be fairly symmetric. We also test the assumption of equality of variances among the different groups using F test of equality of variances. If both these assumptions are satisfied proceed to ANOVA.
If ANOVA results in rejection of null hypothesis and hence we conclude that there is a difference in performance of students in different classrooms, we proceed to Tukey's test to analyse which pairs classrooms differ.