ABSTRACT
Many experiments involve obtaining several measurements on each subject or animal, such as repeatedly measuring its heart rate at several times after being treated. The experimenter generally wants to compare the effect of different treatments or conditions on the subjects and make inferences concerning the effect the treatments have on the relationship between the measured response and time. By repeatedly measuring each subject at the end of several predetermined time intervals, two sizes of experimental units are generated. The subject, which is randomly assigned to one of the treatments, is the large size of experimental unit. By repeatedly measuring each subject at the end of each of d time intervals, the subject or the subject's time in the experiment is "split" into d parts (time intervals) and the response is measured on each part. The smaller size of experimental unit is the interval of time the subject is exposed to the treatment between measurements.
