Several robust absolute deviation statistics have been developed recently. Two such correlation coefficients are developed and discussed, one for ranked data and another for interval level data. The standard error and range of the coefficients are given. The algebraic relationship between the coefficients and three widely used correlation…

Critiques H. W. Marsh and K.-T. Hau's (1996) assertion that parsimony is not always desirable when assessing model-fit on a particular counterexample drawn from Marsh's previous research. This counterexample is neither general nor valid enough to support such a thesis and it signals an oversight of extant, stochastic models justifying correlated…

In response to H. W. Marsh and K.-T. Hau's (1996) article on the potential for inferential errors when parsimony is rewarded in the evaluation of overall fit of structural equation models, a design-sensitive adjustment to the standard parsimony ratio is proposed. This ratio renders a more reasonable upper bound than does the standard parsimony…

Prior standardization of scores when an aggregate score is formed has been criticized. This article presents a demonstration of the effects of differential weighting of aggregate components that clarifies the need for prior standardization. The role of standardization in statistics and the use of aggregate scores in research are discussed.…

The nature of the criterion (dependent) variable may play a useful role in structuring a list of classification/prediction problems. Such criteria are continuous in nature, binary dichotomous, or multichotomous. In this paper, discussion is limited to the continuous normally distributed criterion scenarios. For both cases, it is assumed that the…

Computer simulations indicate that the correlation between baseline and change, by itself, does not invalidate the use of gain scores to measure change, but when the negative correlation is accompanied by decrease in variance from pretest to posttest, covariance is a superior measure of change. (SLD)

Meta-analysis has become an important supplement to traditional methods of research reviewing, although many problems must be addressed by the reviewer who carries out a meta-analysis. These problems include identifying and obtaining appropriate studies, extracting estimates of effect size from the studies, coding or classifying studies, analyzing…

We are concerned with the hypothesis that two variables have a perfect disattenuated correlation, hence measure the same trait except for errors of measurement. This hypothesis is equivalent to saying, within the adopted model, that true scores of two psychological tests satisfy a linear relation. A statistical test of this hypothesis is derived…

Simulated data typical of those from meta analyses are used to evaluate the reliability, Type I and Type II errors, bias, and standard error of the meta-analytic procedures of Schmidt and Hunter (1977). Concerns about power, reliability, and Type I errors are presented. (SLD)

The general linear model was described, and the influence that measurement errors have on model parameters was discussed. In particular, the assumptions of classical true-score theory were used to develop algebraic relationships between the squared multiple correlations coefficient and the regression coefficients in the infallible and fallible…

The present paper suggests that multivariate methods ought to be used more frequently in behavioral research and explores the potential consequences of failing to use multivariate methods when these methods are appropriate. The paper explores in detail two reasons why multivariate methods are usually vital. The first is that they limit the…

The merits of the multilevel model for educational research and its uses for school effectiveness research are considered. The main goal of the paper is to establish what intelligent applications of multilevel models can do, helping researchers decide what they must do to make a rational choice between models. Multilevel models are random line…

This study investigated seven methods for analyzing multivariate group differences. Bonferroni t statistics, multivariate analysis of variance (MANOVA) followed by analysis of variance (ANOVA), and five other methods were studied using Monte Carlo methods. Methods were compared with respect to (1) experimentwise error rate; (2) power; (3) number…