Assessing cross-cultural differences through use of multiple-group invariance analyses

J Pers Assess. 2006 Dec;87(3):249-58. doi: 10.1207/s15327752jpa8703_05.


The use of structural equation modeling in cross-cultural personality research has become a popular method for testing measurement invariance. In this report, we present an example of testing measurement invariance using the Sense of Coherence Scale of Antonovsky (1993) in 3 ethnic groups: Chinese, Japanese, and Whites. In a series of increasingly restrictive constraints on the measurement models of the 3 groups, we demonstrate how to assess differences among the groups. We also provide an example of construct validation.

Publication types

  • Comparative Study
  • Research Support, N.I.H., Extramural

MeSH terms

  • Analysis of Variance
  • Asian Americans / psychology
  • Cross-Cultural Comparison*
  • European Continental Ancestry Group / psychology
  • Humans
  • Models, Statistical
  • Personality Assessment / statistics & numerical data*
  • Personality Inventory / statistics & numerical data
  • Principal Component Analysis
  • Psychometrics / statistics & numerical data*
  • Reproducibility of Results
  • Surveys and Questionnaires