This paper provides an introduction to basic issues concerning structural equation modeling (SEM), a research methodology increasingly being used in social science research. First, seven key issues that must be considered in any SEM analysis are explained. These include matrix of associations to analyze, model identification, parameter estimation…

This paper discusses the issue of multiple testing and overall Type I error rates in contexts other than multiple comparisons of means. It demonstrates, using a 5 x 5 correlation matrix, the application of 5 recently developed modified Bonferroni procedures developed by the following authors: (1) Y. Hochberg (1988); (2) B. S. Holland and M. D.…

The use of a Bayesian approach in evaluating data from clinical trials with many treatment centers and from many studies is discussed. The main distinction between a metaanalysis and an analysis of a multicenter trial is that different studies may have very different designs, while the centers in a multicenter trial usually follow the same…

The position of the "purists" who insist on limiting data to ordinal analysis is contrasted with the "pragmatists" who treat data as interval. (Author)

AN EMPIRICAL STUDY WAS MADE OF THE ERROR FACTORS IN MULTIDIMENSIONAL SCALING (MDS) TO REFINE THE USE OF MDS FOR MORE EXPERT MANIPULATION OF SCALES USED IN EDUCATIONAL MEASUREMENT. THE PURPOSE OF THE RESEARCH WAS TO GENERATE TABLES OF THE SAMPLING DISTRIBUTIONS THAT ARE NECESSARY FOR DISCRIMINATING BETWEEN ERROR AND NONERROR MDS DIMENSIONS. THE…

This paper introduces a model for describing outliers (observations which are extreme in some sense or violate the apparent pattern of other observations) in linear regression which can be viewed as a mixture of a quadratic and a linear regression. The maximum likelihood estimators of the parameters in the model are derived and their asymptotic…

The statistical technique of analyzing data collected at regular intervals to reveal periodic components of the data is described by reference to actual records. The data chosen for illustration include tide height in a river; biochemical oxygen demand and dissolved oxygen in the same river; discharged salt into a river system and its relation to…

An analytic procedure is presented for testing the homogeneity of unstandardized regression weight vectors when the vectors are correlated. The basic design involves repeated measurements on a dependent variable and a set of independent variables. The method is illustrated with a study of perceived leader behavior. (Author/BW)

The authors demonstrate how exponential smoothing can play a role in the identification of the intervention component of an interrupted time-series design model that is analogous to the role that the sample autocorrelation and partial autocorrelation functions serve in the identification of the noise portion of such a model. (Author/BW)

Several possible models for use in attitude scaling are defined and discussed in some detail. Unfolding analysis is illustrated. (DG)

In studies involving judgments of similarity or dissimilarity, a variety of other variables may also be measured. In such cases, there are important advantages to joint analyses of the dissimilarity and collateral variables. A variety of models are described for relating these and algorithms are described for fitting these to data. (Author/JKS)

Problems found in the application of structural equation modeling to the theory of reasoned action are explored, and an alternative model specification is proposed that improves the fit of the data while leaving intact the structural part of the model being tested. Problems and the proposed alternative are illustrated. (SLD)

L. A. Goodman's loglinear formulation for bi-way contingency tables is extended to tables with or without missing cells and is used for exploratory purposes. Three-way tables and generalizations of correspondence analysis are deduced, and a generalized version of Goodman's algorithm is used to estimate scores in all cases. (Author/TJH)

The methodology of P. E. Holland and P. R. Rosenbaum (1986) to assess unidimensionality of binary data is outlined and illustrated through a simulation with 36 items for 2,000 examinees. How to interpret the results is discussed. (SLD)

Responds to "Birth Order and Intelligence: Further Tests of the Confluence Model" by Robert D. Retherford and William H. Sewell. Reviews their arguments and suggests that their analyses of the Wisconsin Longitudinal Study data support rather than contradict the model. (CJS)