Stimulus as a random factor in analysis of variance: Increasing the generalizability of findings
All too often inadequate experimental designs and/or faulty statistical analyses preclude generalization of findings. The authors of this paper discuss the need, in designing studies having educational variables, to give more attention to recognizing the universe of generalization and to incorporating into the design a variable that represents this universe. They further recommend that data analytic techniques, in turn, treat the levels of this variable as randomly selected from the universe.
KeywordsEducational Technology Random Factor Internal Combustion Engine American Educational Research Journal Instructional Unit
Unable to display preview. Download preview PDF.
- Coleman, E. B. Generalizing to a language population.Psychological Reports, 1964,14, 219–226.Google Scholar
- Dwyer, F. M. The effect of IQ level on the instructional effectiveness of black-and-white and color illustrations.AV Communication Review, 1976,24, 49–61.Google Scholar
- Sells, S. B. (Ed.).Stimulus determinants of behavior. New York: Ronald Press, 1963.Google Scholar
- Winer, B.J. Statistical principles in experimental design. McGraw-Hill: New York, 1971.Google Scholar