Multilevel models are often used to evaluate hypotheses about relations among constructs when data are nested within clusters (Raudenbush & Bryk, 2002), although alternative approaches are available when analyzing nested data (Binder & Roberts, 2003; Sterba, 2009). The overarching goal of this article is to suggest when it is appropriate…

We present a new paradigm that allows simplified testing of multiparameter hypotheses in the presence of incomplete data. The proposed technique is a straight-forward procedure that combines the benefits of two powerful data analytic tools: multiple imputation and nested-model ?2 difference testing. A Monte Carlo simulation study was conducted to…

Many methods exist for imputing missing data but fewer methods have been proposed to test the missing data mechanism. Little (1988) introduced a multivariate chi-square test for the missing completely at random data mechanism (MCAR) that compares observed means for each pattern with expectation-maximization (EM) estimated means. As an alternative,…

When laws change the rules of the game, it is important to observe the effects on the players' behavior. Some effects can be anticipated while others are difficult to enunciate before the law comes into force. In this paper we have analyzed articles authored by Spanish accounting academics between 1996 and 2005 to assess the impact of a change in…

Two basic data sources required for research studies have been secondary and primary. Secondary data collection helps the researcher to provide relevant background to the study and are, in most cases, available for retrieval from recorded sources. Primary data collection requires the researcher to venture into the field where the study is to take…

The authors argue that a parameterization in terms of cell means is a useful conceptual device for resolving problems inherent in the nonorthogonal analysis of variance. They demonstrate their argument by considering two widely-used methods for testing main effects. (Author/BW)

The basic notion of variability is generalized from a univariate context to a multivariate context using two matrix functions, a determinant, and a trace, yielding a number of alternative multivariate indices of shared variation. Some problems in the interpretation of tests of multivariate hypotheses are reviewed. (Author/BW)

The recommendation to use group means when there may be nonindependence among observational units is unduly restrictive. When random factors are properly identified and included in the analysis, the results are identical in balanced analysis of variance designs, irrespective of whether group means or individual observations are employed.…

Analyzes the logical basis of testing developmental order hypotheses with categorical measures. Argues that depending on whether saltatory or continuous developmental changes are being assessed, the observed relationship between categorical measures yields different types of information about developmental ordering. Maintains that when change is…

Preparation of this paper facilitated by Grant GS-1741 from the Division of Social Sciences of the National Science Foundation.

When analysis of variance is used, statistically significant differences may or may not be of practical significance to educators. A large part of the problem is due to the fact that a "zero difference" null hypothesis can always be rejected statistically if the sample size is large enough. If, however, a method based on the noncentral F…

Suggests that testing developmental ordering hypotheses is difficult because rare use of ratio scales prevents direct comparison of measures. Demonstrates that the observed data pattern is constrained by the underlying relationship--although observed data pattern may not reflect the exact relationship, it limits possible relationships. Shows the…

Theories employed to explain regularities in social behavior often contain explicit or implicit reference to the presence of nonlinear and/or nonadditive (i.e., multiplicative) relationships among germane variables. While such nonadditive features are theoretically important, the inclusion of quadratic or multiplicative terms in structural…

Hypothesis generation and testing is outlined as an additional domain for program evaluators. Program evaluation involves a thorough analysis of the processes that contribute to change (or a lack of change) among program recipients. This process of change is analyzed in two ways: (1) treating programs as naturally occurring field studies; and (2)…

An investigation was conducted of the characteristics of two estimation procedures and corresponding test statistics used in the analysis of completely randomized factorial experiments when observations are lost at random. For one estimator, contrast coefficients for cell means did not involve the cell frequencies. For the other, contrast…