Purpose: to test whether the means of k (cid:523)(cid:951) (cid:884)(cid:524) populations significantly differ. H1: not all "s are the same (cid:523)at least one of the means is different(cid:524) We never have to make any assumptions about the sample. Because we have this information on hand, so we can always verify for ourselves. When we make assumptions, we are making assumptions about entire populations because it is usually impossible for us to look at all observations in a given population. We make assumptions about a population based on a sample of this population. The distribution of observations on the dependent variable is normal within each group. The variances of observations are equal (homogeneity of variance) You can have three populations of exam scores. The first assumption is that all these populations follow a normal distribution. The second assumption is that these normal distributions will have exactly the same variance.