New publication on PLS-SEM
The article titled "Heuristics versus statistics in discriminant validity testing: A comparison of four procedures,“ authored by George Franke (University of Alabama) and Marko Sarstedt has been accepted for publication in Internet Research, a leading journal in the management information systems field (impact factor: 2.93). This study reviews and extends recent simulation studies on discriminant validity measures, contrasting the use of cutoff values (i.e., heuristics) with inferential tests. Based on a simulation study, which considers different construct correlations, sample sizes, numbers of indicators, and loading patterns, the study assesses each criterion’s sensitivity to type I and type II errors. The findings provide further evidence for the robustness of the heterotrait-monotrait ratio of correlations (HTMT) criterion as an estimator of disattenuated (perfectly reliable) correlations between constructs, whose performance parallels that of the standard constrained Phi approach. Furthermore, the study dentify situations in which both methods fail and suggest an alternative criterion.
Franke, George and Sarstedt, Marko (2018). "Heuristics versus statistics in discriminant validity testing: A comparison of four procedures,“ Internet Research, forthcoming.