figure A-11 Two pairs of distributions that differ in variability Notice how little variability exists within each of the groups in (a); the manipulation seemed to have the effect of making everyone in each of the groups look very similar. Note also that, because there is little variability within the groups, there is very little overlap between these two distributions of scores. The frequency distributions in (b) represent what would happen if the two samples still differed, on average, but had a lot more variability within them. This increase in variability increases the amount of overlap between the two distributions of scores. If they do differ, on average, chance is probably playing a role.