The recent article on statistics and scientific methods by Thorpe and Baker,1 while generally sound, contains some arguments which could be misleading to the practitioner without formal experimental training. These arguments revolve around the meaning of the word “population” in research. A population is the total supply or “universe” of a particular kind of subject matter. Populations, like concepts, have to be defined operationally for experimental purposes.
The population definition ordinarily begins, “All the people who . . .,” and it is usually taken for granted that the number will be quite large. This is not necessary in theory. The absolute size of “all” is relative. Populations are defined arbitrarily, depending upon the purposes of the individual experimenter or theorist. A population could be defined equally validly as “all the paranoid schizophrenics in the world at any given moment,” or “all the paranoid schizophrenics who
LEVITT EE. "Statistics, Science, and Psychiatry": A Comment. AMA Arch Gen Psychiatry. 1960;2(4):457–458. doi:10.1001/archpsyc.1960.03590100097010
Artificial Intelligence Resource Center
Customize your JAMA Network experience by selecting one or more topics from the list below.