5. Conclusion
As a family of statistical methods, structural equation modeling is still young. The factor-based approach to SEM spread rapidly across the social sciences (Bentler, 1986), while PLS path modeling emerged later and developed more slowly, perhaps due to the absence of strong software. Regardless, much of the “received wisdom” on SEM has a limited evidentiary base for support. More than that, the emergence of SEM invited researchers to think in new ways, at new levels of abstraction. Analogies and heuristics are powerful tools in helping people to come to grips with things that are new and difficult to understand. While useful, however, heuristics can also be misleading. The more fundamental technology of null hypothesis significance testing is itself widely misunderstood, with textbooks enshrining mistakes as basic principles and infecting whole generations of researchers with falsehoods and confusion (Gigerenzer, 2004; Ziliak & McCloskey, 2008). Regarding factor analysis, Stewart (1981, p. 51) noted a similar state: “So widespread are current misconceptions about factor analysis in the marketing community that even its defenders and some prominent reviewers perpetuate misinformation.” The same might be said of both factor-based and composite-based approaches to SEM today. Saunders and Bezzina's (2015) “methodological tribalism” appears to separate quantitative methods communities just as much as it separates quantitative from qualitative. It should be clear to European management researchers that PLS path modeling is not a panacea for flaws in research design or execution. It does not multiply a small sample size into a large one. It does not transform a poorly conceived approach into a piercing, insightful analysis. At the same time, PLS path modeling is not a flawed analytical method. It may be misunderstood, but probably is no more so than the factor-based approach to SEM, or any other sophisticated data analysis technique.
