Measurement Issues in Cross-Cultural Social Work Research

With demographic changes and the reality of cultural diversity in the United States of America and other parts of the world today, social work researchers are increasingly aware of the need to conduct cross-cultural research and evaluation whether for hypothesis testing or outcome evaluations. To ensure the quality of data collection and validity of outcomes, social work researchers must have both reliable and valid research instruments and measurements.

This workshop aims to provide an overview of issues and techniques of cross-cultural measures and to provide the participants with a step-by-step approach to the assessment of cross-cultural equivalence of measurement properties.

The presenter will describe the process of cross-cultural instrument development, from formulating the research aims to the assessments of cross-cultural measurement properties. Participants will learn the methods of adopting and adapting existing research instruments. The processes and issues of cross-cultural translation and assessments will be presented and discussed in details. The workshop addresses the foundation of measurement theories and the entire process of instrument development from the definitions of abstract concepts, the construction of observed indicators, and assessment of the validity and reliability of the new instruments.

Researchers have proposed different procedural steps in the testing of measurement equivalence hypotheses, including the equivalence of the covariance matrices of the observed indicators and the equivalence of factor means among groups. Joreskog and Sorbom (2001) recommend the testing of five general hypotheses, including equivalence of covariance matrices of observed indicators of a scale or an instrument; equivalence of factor patterns of observed indicators; equivalence of factor loadings of observed indicators on their respective factors; equivalence of measurement errors of observed indicators; and equivalence of factor variances and covariance across groups. Invariance of factor pattern and factor loadings is sufficient to determine whether a construct can be measured across different cultural, national, or racial groups.

Participants will learn the applications of item distribution analysis, internal consistency analysis, and exploratory factor analysis and confirmatory factor analyses as the preferred methods of cross-cultural equivalence evaluation of research instruments. In addition, the presenter will explain and illustrate the application of multisample confirmatory factor analysis to evaluate the factor structure and testing of cross-cultural measurement invariance.

Participants are expected to have a basic understanding of descriptive statistics and some knowledge of factor analysis. At the end of the workshop, participants will have basic understanding of cross-cultural measurement issues, become familiar with both basic and advanced techniques of cross-cultural assessments of research measurements. Hand on learning materials will be available at the workshop (Tran, 2009).