摘要：Institutional trust is often measured by several items that are analyzed individually or as sum-scores. However, it is difficult to summarize the results of individual-items analyses, whereas sum-scores may be meaningless if the dimensions that the items are assumed to measure are not verified. Although these limitations are circumvented by using factor analysis, response styles may still bias research results. We use data from Guyana to show that a second-order factor model is appropriate for measuring institutional trust. We also demonstrate that response styles can inflate item and factor convergent validity and may either distort regression effects or create completely spurious ones. We therefore recommend using factor models with corrections for response styles in institutional trust research instead of sum-scores and individual-items analyses.
