ABSTRACT
In ‘Student’s t test’ (p. 110) it was described how the t test could be used to compare the means of two groups. But what if there are more than two groups? It would not be appropriate to compare every combination of the groups in pairs by using multiple t tests. To do so would result in an increased risk of making a type I error. Instead an ANOVA (analysis of variance) table can be used to test for a difference in the mean outcome level between three or more groups. We define k as the number of groups, the mean of the ith group, ni as the number of observations for group i and N as the total number of observations. Additionally, yij is the jth observation of the ith group.
