The superego, the ego., and id in statistical reasoning

Piaget worked out his logical theory of cognitive development, Koehler the Gestalt laws of perception, Pavlov the principles of classical conditioning, Skinner those of operant conditioning, and Bartlett his theory of remembering and schemata - all without rejecting null hypotheses. But, by the time I took my first course in psychology at the University of Munich in 1969, null hypothesis tests were presented as the indispensable tool, as the sine qua non of scientific search. Post-World War 2 German psychology mimicked a revolution of research practice that had occurred between 1940 and 1955 in American psychology. What I learned in my courses and textbooks about the logic of scientific inference was not without a touch of morality, a scientific version of the 10 commandments: Thou shalt not draw inferences from a nonsignificant result. Thou shalt always specify the level of significance before the experiment; those who specify it afterward (by rounding up obtained p values) are cheating. Thou shalt always design the experiments so that thou canst perform significance testing.