摘要

Domain importance weighting has long been a topic of debate in the study of quality of life (QoL). The purpose of this study is to examine the adequacy of popular approaches used to assess domain importance weighting with QoL measures that follow a formative-indicator approach. Using both empirical and simulation data, this study found that neither of the two popular methods of evaluating the performance of domain importance weighting in QoL measures, correlation and moderated regression analysis, was ideal in capturing the actual function domain importance weighting posited in the data. More specifically, results from the popular approaches used to assess domain importance weighting could be quite misleading when QoL measures were constructed using a formative-indicator approach. These findings call for a careful re-examination of results from previous studies using those popular approaches to assess domain importance weighting in QoL measures.

  • 出版日期2014-3