When a statistician or a researcher in any field designs a study, there are many concepts which he must clarify in his own mind before the study is started. He must define his problem, his target population, and his statistical unit, decide on how he is going to take a sample and what he is going to do with it when he gets it, realize what problems can arise because of the manner in which the sample is selected, and he must decide how to collect, tabulate, and analyze the data, and what kinds of conclusions he could draw. When a statistician evaluates a study done by someone else, he obviously must look at the same concepts to see whether the conclusions drawn follow logically from what was done in terms of the manner in which these concepts were defined. I would like to take the University Group Diabetes Program
No takes yet. Share an insight, caveat, or question.
S. Schor (1971) studied this question.