This chapter presents a review of applications of structural equation modeling (SEM) published in psychological research journals in recent years. We focus first on the variety of research designs and substantive issues to which SEM can be applied productively. We then discuss a number of methodological problems and issues of concern that characterize some of this literature. Although it is clear that SEM is a powerful tool that is being used to great benefit in psychological research, it is also clear that the applied SEM literature is characterized by some chronic problems and that this literature can be considerably improved by greater attention to these issues.

Applications of Structural Equation Modeling in Psychological Research

The empirical short-form literature has been characterized by overly optimistic views of the transfer of validity from parent form to short form and by the weak application of psychometric principles in validating short forms. Reviewers have thus opposed constructing short forms altogether, implying researchers are succumbing to an inappropriate temptation by trying to abbreviate measures. The authors disagree. The authors do not oppose the development of short forms, but they do assert that the validity standards for short forms should be quite high. The authors identify 2 general and 9 specific methodological sins characterizing short-form construction and offer methodological suggestions for the sound development of short forms. They recommend a set of 6 a priori steps researchers should consider and 9 methodological procedures researchers can use to develop valid abbreviated forms of clinical-assessment procedures.

On the sins of short-form development.

The study aimed to investigate the effectiveness of a new multi-component social skills intervention for children with Asperger syndrome (AS): The Junior Detective Training Program. This 7-week program included a computer game, small group sessions, parent training sessions and teacher handouts. Method: Forty-nine children with AS were recruited to participate and randomly assigned to intervention (n = 26) or wait-list control (n = 23) conditions. Results: Relative to children in the wait-list group, program participants showed greater improvements in social skills over the course of the intervention, as indicated by parent-report measures. Teacher-report data also confirmed that children receiving the intervention made significant improvements in social functioning from pre-to posttreatment. Treatment group participants were better able to suggest appropriate emotion-management strategies for story characters at post-intervention than at pre-intervention, whereas control participants were not. However, there was no difference in the improvements made by children in the intervention and control conditions on facial expression and body-posture recognition measures. Follow-up data suggested that treatment gains were maintained by children at 5-months post-intervention. Conclusions: The Junior Detective Training Program appeared to be effective in enhancing the social skills and emotional understanding of children with AS. Limitations and suggestions for future research are discussed.

A multi-component social skills intervention for children with Asperger syndrome: the Junior Detective Training Program.

Attention-deficit/hyperactivity disorder: a preliminary diffusion tensor imaging study.

Children with high-functioning autism earned above normal scores on the Wechsler Intelligence Scale for Children-Fourth Edition (WISC-IV) Perceptual Reasoning and Verbal Comprehension Indexes and below normal scores on the Working Memory and Processing Speed Indexes and Wechsler Individual Achievement Test-Second Edition (WIAT-II) Written Expression. Full Scale IQ (FSIQ) and reading and math scores were similar to the norm. Profiles were consistent with previous WISC-III research, except that the new WISC-IV motor-free visual reasoning subtests (Matrix Reasoning and Picture Concepts) were the highest of the nonverbal subtests. The WISC-IV may be an improvement over the WISC-III for children with high-functioning autism because it captures their visual reasoning strength, while identifying their attention, graphomotor, and processing speed weaknesses. FSIQ was the best single predictor of academic achievement.

WISC-IV and WIAT-II Profiles in Children With High-Functioning Autism

Using specific theoretical and practical criteria, 8 subtests were selected from the Wechsler Intelligence Scale for Children-Third Edition (WISC-III; D. Wechsler, 1991) to construct a short form that would allow computation of all 4 factor index scores. Linear scaling was used to compute deviation quotients of the short form, and confirmatory factor analysis was used to determine which of 6 hypothesized models could best explain intelligence as measured by this WISC-III short form. The results indicated that the short form had satisfactory reliability and validity and that a 4-factor model (composed of Verbal Comprehension, Perceptual Organization, Freedom From Distractibility, and Processing Speed) fit the data of this short form relatively best. Specific guidelines for use of this short form in clinical practice are provided.

A Short Form of the WISC-III for Clinical Use.

Representative profile subtypes, based on factor index scores, were examined in the standardization sample of the Wechsler Intelligence Scale for Children-Third Edition (WISC-III; Wechsler, 1991). Two-stage cluster analysis identified 5 reliable subtypes. Three of these were differentiated by levels of performance (ranging from below average, to average, to above average); the other 2 were characterized by patterns of performance, with relative efficacy on the processing speed factor being the most prominent distinction (ranging from a relative weakness to a relative strength). The cluster subtypes did not differ significantly in age, but parental level of education covaried directly with level of WISC-III performance. A method for determining the relative uniqueness of clinically obtained WISC-III factor index score patterns is presented.

Jacques Donders

Papers

A Short Form of the WISC-III for Clinical Use.

Cluster Subtypes in the WISC-III Standardization Sample: Analysis of Factor Index Scores.