This article reviews some of the properties of criterion-scaled regression analysis, especially as it relates to the analysis of a repeated measures/randomized block design. (Author/LMO)

Estimators which are optimal under assumptions of normality are shown to be vulnerable to the effects of outliers. A survey of robust alternatives is presented. Included are alternatives to the mean, standard deviation, product-moment correlation, t-test, analysis of variance, multivariate techniques, and schemes for outlier detection. (Author/JKS)

The controversy surrounding regression methods for unbalanced factorial designs is addressed. The statistical hypotheses being tested under the various methods, as well as salient issues in the use of these methods, are discussed. The use of statistical computer packages is also discussed. (Author/JKS)

Discussion of journal article titles as an index to the contents, and thus to the underlying discipline, focuses on a study that was conducted to investigate the development of the field of counseling. Use of the Danielson and Bryan Index is described, and implications of a trend toward longer titles are suggested. (11 references) (LRW)

Recent criticism in the literature of the use of inferential statistics in educational research is refuted. The authors focus on the defense of multiple regression analysis. (JKS)

Three linear models (Fixed, Random, and Provisional) and their inferential counterparts are presented and discussed. The three linear models are considered in relation to the analysis of nonlinearity, and limitations in the use of polynominal and product variables are discussed. Several exemplary research papers are examined and reconsidered in…

Similarities between regression analysis and analysis of variance are noted and it is argued that the former has advantages over the latter. It is also argued that canonical correlation analysis is more suitable than factor analysis in certain cases. The argument is illustrated with four recent pieces of educational research. (DG)

The purposes of this paper are to provide an explanation of the way in which suppressor variables operate in multiple regression, and to provide illustrations of their effects with actual social science data. Examples are reviewed in which one predictor accounts for more of the variance in the dependent variable when another predictor is included,…

Brief descriptions are provided of general-purpose mathematical and statistical software, including 27 "stand-alone" programs, three subroutine systems, and two nationally recognized statistical packages, which are available in the Air Force Human Resources Laboratory (AFHRL) software library. This index was created to enable researchers…

Two theorems concerning F in analysis of covariance with two groups (experimental and control) and one covariable (pretest score) are presented. The first shows explicitly that F is a direct function of the ratio of the variance about the regression line for the total sample to the variance about the within-group regression line. The second…

In this paper problems caused by the existence of errors of measurement are identified for factor analysis, regression analysis, ANOVA, and ANCOVA. At least one detrimental effect is shown to exist for each type of analysis. When a researcher's interest is with infallible variables, he runs the risk of biased results from all of the procedures…

With even the simplest bivariate regression, least-squares solutions are inappropriate unless one assumes a priori that reciprocal effects are absent, or at least implausible. While this discussion is limited to bivariate regression, the issues apply equally to multivariate regression, including stepwise regression. (Author/CTM)

Different approaches to defining suppression in multiple regression/correlation are compared, and their differences are illustrated. A test for determining the significance of a suppressor effect, which is based on the definition of suppression of W. F. Velicer, is extended to the general multiple predictor case and analysis of variance. (SLD)

Explores the effects of task characteristics and structural characteristics on aspects of information processing based on a survey of employees in the Australian telecommunications industry. Relevant research is reviewed; the analysis of results is explained; and implications for organizations are suggested. (Contains 42 references.) (LRW)

The degree to which the chosen units of analysis are likely to produce spurious findings in staged combinations of multiple linear regression procedures are examined. The effects of grouping variables (e.g., classroom, school, and school district) on Procedures such as Coleman's semipartial regression and Mayeske's commonalities, in light of…