An analysis of the relative merits of the normative and experimental approach to research shows that there is much potential confounding by unknown variables with both designs. The results of the analysis are interpreted as casting considerable doubt about the ability of experimental studies in psychology to be unaffected by unknown variables.
Get full access to this article
View all access options for this article.
References
1.
CochranW. G.CoxG.Experimental designs. (2nd ed.) New York: Wiley, 1957.
2.
EdgingtonE. S.Implications of symmetry around a regression line. Percept. mot. Skills, 1966, 23, 321–322.
3.
MyersJ. L.Fundamentals of experimental design. Boston: Allyn & Bacon, 1966.
4.
WilkM. B.KempthorneO.Fixed, mixed and random models. J. Amer. Stat. Assn, 1955, 50, 1144–1167.
5.
WinerB. F.Statistical principles in experimental design. New York: McGraw-Hill, 1962.
