Predicting the performance of measures in a confirmatory factor analysis with a pretest assessment of their substantive validities
Article Abstract:
A pretest methodology for predicting the performance of measures in a confirmatory factor analysis is presented. A pretest item-sort task draws on the concept of substantive validity, and two indices of substantive validity in a theory-testing context are proposed: the proportion of substantive agreement, p (sub. sa), and the substantive-validity coefficient, c(sub. sv). The utility of this method is empirically illustrated with a postdictive study of impulsivity measures. Results from two pretest samples of 20 respondents provided significant support for the use of substantive-validity coefficient values to discriminate measures that would be retained in a subsequent confirmatory factor analysis from those that would not. In addition, significant evidence was found for the reproducibility of each substantive-validity index across the two samples. Issues to be considered when using the pretest methodology and some benefits of assessing the substantive validity of measures for construct definitions and delineation of content domains are discussed. (Reprinted by permission of the publisher.)
Publication Name: Journal of Applied Psychology
Subject: Social sciences
ISSN: 0021-9010
Year: 1991
User Contributions:
Comment about this article or add new information about this topic:
Maximum likelihood confirmatory factor-analytic investigation of factors within Guilford's structure of intellect model
Article Abstract:
Joreskog's confirmatory factor-analytic methodology was used to statistically test alternative hypotheses regarding the factor structure among tests of cognition, convergent production, and divergent production that underlies correlational data from the Aptitude Research Project. Large substantive improvements in goodness-of-fit indexes over random multifactor or general (single) factor models were not found, hence, the structure-of-intellect (SI) a priori models did not provide a superior fit to the data. The conclusion is that neither the high-dimensional SI model nor the general factor model provided a plausible level of overall fit to the data. Suggestions for future research and results of exploratory factor analyses are presented. (Reprinted by permission of the publisher.)
Publication Name: Journal of Applied Psychology
Subject: Social sciences
ISSN: 0021-9010
Year: 1989
User Contributions:
Comment about this article or add new information about this topic:
- Abstracts: Specification of the criterion construct space: an application of hierarchical confirmatory factor analysis. Statistical control of halo: clarification from two cognitive models of the performance appraisal process
- Abstracts: Estimates of the dollar value of employee output in utility analyses: an empirical test of two theories. Biographical data in employment selection: can validities be made generalizable?
- Abstracts: Structure of drug use behaviors and consequences among young adults: multitrait-multimethod assessment of frequency, quantity, work site, and problem substance use
- Abstracts: Understanding prosocial behavior, sales performance, and turnover: a group-level analysis in a service context
- Abstracts: Information requests in the context of escalation. De-escalation of commitment in oil exploration: when sunk costs and negative feedback coincide