Archives: Articles

IssueM Articles

(2) Some Comments on “The Unit of Analysis: Group Means Versus Individual Observations”

R. Clifford Blair
University of South Florida

J. J. Higgins
Kansas State University

Abstract: Hopkins (1982) has criticized the use of means as the unit of analysis in situations where intact groups (e.g. classes) rather than individuals have been randomly assigned to various treatment conditions. Instead Hopkins advocates the use of certain ANOVA models which, insofar as tests for treatment effects are concerned, yield results that are equivalent to those that would be obtained if class means were employed as the unit of analysis. This paper points out that, because of the nonrobustness of the sample mean as an estimator of location, use of the class mean as the unit of analysis or of the ANOVA models advocated by Hopkins can lead to larger than necessary Type II error rates in tests of significance for treatment effects. This paper also shows how, in the nonnormal population situation, use of summary statistics other than the mean (e.g. members of the family of trimmed means) can lead to significant increases in the power of tests for treatment effects. It is also suggested here that the pooling options offered by Hopkins should be viewed with caution.

Citation: Blair, R. C., & Higgins, J. J. (1984). Some comments on “the unit of analysis: group means versus individual observations”. Florida Journal of Educational Research, 26(1), 5-20.

Download:  Blair.261.pdf (964 downloads )

(1) Teachers’ Sense of Efficacy: A Self- or Norm-Referenced Construct?

Patricia Ashton
University of Florida

Dianne Buhr
University of Florida

Linda Crocker
University of Florida

Abstract: Two approaches to the measurement of teacher efficacy were investigated to determine whether teachers’ sense of efficacy is a self- or a norm-referenced construct. Two forms of an instrument consisting of 25 teaching problem situations were developed: one required self-referenced while the other required norm-referenced responses. The two forms were randomly distributed to 65 classroom teachers enrolled in graduate classes at the University of Florida. In addition, two items measuring teacher efficacy from a Rand Corporation study and the Marlowe-Crowne Scale of Social Desirability were administered. Efficacy appears to be a norm-referenced rather than a self-referenced construct. Social desirability bias was a significant factor in the use of self-referenced vignettes.

Citation: Ashton, P., Buhr, D., & Crocker, L. (1984). Teachers’ sense of efficacy: a self- or norm-referenced construct? Florida Journal of Educational Research, 26(1), 29-41.

Download:  Ashton.261.pdf (1153 downloads )

(6) On the Relative Power of Interaction Analysis

Richard L. Tate
Florida State University

Abstract: It is argued that statements in the current literature suggesting that interaction effects are, in general, as easy to detect as main effects are misleading. Different effect definitions which produce different conclusions about the relative power of interaction analysis are considered for both factorial ANOVA and aptitude-treatment-interaction models. Based on what is defined as a reasonable specification of “comparable” effects, it is concluded that the power for simple main and interaction effects is, in general, lower than that for the analysis of main effects.

Citation: Tate, R. L. (1983). On the relative power of interaction analysis. Florida Journal of Educational Research, 25(1), 1-13.

Download:  Tate.251.pdf (1028 downloads )