Many clinical and social psychologists need to develop scales to carry out their research. Without adequate training in psychometric methods, they can easily run into difficulty. This article is designed to address some of the more common pitfalls in homogeneous scale construction. Empirical scale development by the criterion-group method is not considered. Suggestions are offered about item writing, answer scale formats, data analysis procedures, and overall scale development strategy. Particular emphasis is placed on the effective use of factor-analytic methods to select items for the scale and to determine its proper location in the hierarchy of factor constructs.
This article reviews methodological issues that arise in the application of exploratory factor analysis (EFA) to scale revision and refinement. The authors begin by discussing how the appropriate use of EFA in scale revision is influenced by both the hierarchical nature of psychological constructs and the motivations underlying the revision. Then they specifically address (a) important issues that arise prior to data collection (e.g., selecting an appropriate sample), (b) technical aspects of factor analysis (e.g., determining the number of factors to retain), and (c) procedures used to evaluate the outcome of the scale revision (e.g., determining whether the new measure functions equivalently for different populations).
We administered the Cattell 16 Personality Factor Questionnaire (16 PF), the Comrey Personality Scales (CPS), and the Eysenck Personality Inventory (EPI) to a sample of 669 Australians that was controlled in composition for age, sex, and social class. Factor analyses derived from analyzing scales of the three inventories in the same matrix produced a group of factors that were similar to the five robust factors of personality found in studies that used ratings by others. Two of the factors were similar to the two EPI scales and five were similar to five of the eight CPS scales. One of these five factors was similar to a single 16 PF scale. The 16 PF scales were highly overlapping and factorially complex, an indication that fewer than 16 separate constructs are measured at the primary level. There were, however, clear relations between the five factors and the second-order factor structure of the 16 PF, as Karson and O'Dell (1976) described.
Previous research has suggested that generalized internality-externality is related to cautious behavior, but attempts to relate Rotter's Internality-Externality (I-E) scale to driving accidents have been disappointing. Scales of intemality and externality specifically oriented to driving behavior were
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.