Hwang, HeungsunHeungsunHwangSarstedt, MarkoMarkoSarstedtCheah, Jun HwaJun HwaCheahRingle, Christian M.Christian M.Ringle2019-12-112019-12-112020-01Behaviormetrika 47: 219-241 (2020-01)http://hdl.handle.net/11420/3980Partial least squares path modeling (PLSPM) and generalized structural component analysis (GSCA) constitute composite-based structural equation modeling (SEM) methods, which have attracted considerable interest among methodological and applied researchers alike. Methodological extensions of PLSPM and GSCA have appeared at rapid pace, producing different research streams with different foci and understandings of the methods and their merits. Based on a theoretical comparison of PLSPM and GSCA in terms of model specification, parameter estimation, and results evaluation, we apply a text analytics technique to identify links between dominant topics in methodological research on both methods. We find that researchers have put effort on clearly distinguishing factor and composite models and their implications for the methods’ performance. We also identify an increasing interest in more complex model specifications such as mediating effects and higher-order models. The evidence of converging and diverging PLSPM and GSCA streams of research points out opportunities for advancing the evolution of composite-based SEM.en1349-69642020Springer JapanCompositesGSCALeximancerPLSPMScientometricsText analyticsWirtschaftJournal Article10.1007/s41237-019-00085-5Other