Exploring Nonlinear Models in Personality Assessment: Development and Preliminary Validation of a Negative Emotionality Scale


  • The authors express their gratitude to Brian Kojetin, Matt McGue, Abigail Panter, Irwin Waldman, and Stephen West for useful comments on earlier versions of this article. Special thanks are due to Leona Aiken for superb editorial assistance and to Scientific Software for providing a review copy of TESTFACT. This article is dedicated to the memory of Jeffrey S. Tanaka.

Address correspondence to Niels G. Waller, Department of Psychology, University of California, Davis, CA 95616. NG WALLER@UCDAVIS.EDU.


ABSTRACT In this article we discuss the applicability of several new measurement models to the construction of personality scales, and we contrast these models with more traditional approaches in common usage, such as the principal factor analysis model. Our goal is to illustrate how nonlinear item-response models can be profitably used in personality research. We describe the development of a 30-item Negative Emotionality scale that was constructed using nonlinear factor analysis and item-response theory. We also show how traditional (linear) factor analysis can produce misleading results when it is applied to personality items with dichotomous response formats (e.g., true/false, agree/disagree). No formal training in modern measurement theory is assumed of the reader as we describe the nonlinear models that are used in this study in nontechnical language with a minimum of mathematics.