Let's assume you are conducting an experiment to determine the effect of a new drug on the incidence of epileptic seizures. You select 20 epileptics from the 150 epileptics being treated at a nearby hospital and administer the drug to them. You record the number of seizures in each of the 20 subjects for one month. Then you record the number of seizures in each of the 20 subjects for one month without the drug. Being compulsive, you also record the number of seizures for the remaining 130 epileptics for one month. The number of seizures for each of the 130 epileptics constitutes