To determine whether a new sleeping pill has an affect that varies with dosage, a researcher randomly assigns adult insomniacs, in equal numbers, to receive either 4 or 8 grams of the sleeping pill. The amount of sleeping time is measured for each subject during an 8-hour period after the administration of the dosage. What type of design is this, and what type of statistic is needed to analyze the data (consider ABAB studies)?

Let's imagine that we added a group that received 12 grams... how would this change the analysis?