Statistics for Small Groups: The Power of the Pretest

Abstract

In the area of severe-profound retardation, researchers are faced with small sample sizes. The question of statistical power is critical. In this article, three commonly used tests for treatment-control group differences are compared with respect to their relative power: the posttest-only approach, the change-score approach, and an analysis of covariance (ANCOVA) approach. In almost all cases, the ANCOVA approach is the more powerful than the other two, even when very small samples are involved. Finally, a fourth approach involving ANCOVA plus alternate rank assignments is examined and found to be superior even to the ANCOVA approach, especially in small sample cases. Use of slightly more sophisticated statistics in small sample research is recommended.

Keywords

data analysis methodology

Get full access to this article

View all access options for this article.

References

Arvey

Cole

Hazucha

Hartanto

(1985). Statistical power of training evaluation designs. Personal Psychology, 38, 493–507.

Blair

(1981). A reaction to “consequences of failure to meet assumptions underlying the fixed effects analyses of variance and covariance.” Review of Educational Research, 51, 499–507.

Cohen

(1977). Statistical power analysis for the behavioral sciences (rev. ed.). New York: Academic Press.

Dalton

Overall

(1977). Nonrandom assignment in ANCOVA: The alternate ranks design. The Journal of Experimental Education, 46, 58–62.

Feldt

(1958). A comparison of the precision of three experimental designs employing a concomitant variable. Psychometrika, 23, 335–353.

Huck

McLean

(1975). Using a repeated measures ANOVA to analyze data from a pretest-posttest design: A potentially confusing task. Psychological Bulletin, 82, 511–518.

Maxwell

Delaney

Dill

(1984). Another look at ANCOVA versus blocking. Psychological Bulletin, 95, 136–147.

Maxwell

Howard

(1981). Change scores—necessarily ANATHEMA? Educational and Psychological Measurement, 41, 747–756.