Convergent validity assessment of formatively measured constructs in PLS-SEM: On using single-item versus multi-item measures in redundancy analyses

Researchers often use partial least squares structural equation modeling (PLS-SEM) to estimate path models that include formatively specified constructs. Their validation requires running a redundancy analysis, which tests whether the formatively measured construct is highly correlated with an alternative measure of the same construct. Extending prior knowledge in the field, this paper aims to examine the conditions favoring the use of single vs multiple items to measure the criterion construct in redundancy analyses.

Merging the literatures from a variety of fields, such as management, marketing and psychometrics, we first provide a theoretical comparison of single-item and multi-item measurement and offer guidelines for designing and validating suitable single items. An empirical comparison in the context of hospitality management examines whether using a single item to measure the criterion variable yields sufficient degrees of convergent validity compared to using a multi-item measure.

The results of an empirical comparison in the context of hospitality management show that, when the sample size is small, a single item yields higher degrees of convergent validity than a reflective construct does. However, larger sample sizes favor the use of reflectively measured multi-item constructs, but the differences are marginal, thus supporting the use of a global single item in PLS-SEM-based redundancy analyses.

This study is the first to research the efficacy of single-item versus multi-item measures in PLS-SEM-based redundancy analyses. The results illustrate that a convergent validity assessment of formatively measured constructs can be implemented without triggering a pronounced increase in survey length.