Fl. Schmidt, STATISTICAL SIGNIFICANCE TESTING AND CUMULATIVE KNOWLEDGE IN PSYCHOLOGY - IMPLICATIONS FOR TRAINING OF RESEARCHERS, Psychological methods, 1(2), 1996, pp. 115-129
Data analysis methods in psychology still emphasize statistical signif
icance testing, despite numerous articles demonstrating its severe def
iciencies. It is now possible to use meta-analysis to show that relian
ce on significance testing retards the development of cumulative knowl
edge. But reform of teaching and practice will also require that resea
rchers learn that the benefits that they believe flow from use of sign
ificance testing are illusory. Teachers must revamp their courses to b
ring students to understand that (a) reliance on significance testing
retards the growth of cumulative research knowledge; (b) benefits wide
ly believed to flow from significance testing do not in fact exist; an
d (c) significance testing methods must be replaced with point estimat
es and confidence intervals in individual studies and with meta-analys
es in the integration of multiple studies. This reform is essential to
the future progress of cumulative knowledge in psychological research
.