Prediction-Oriented Model Selection in Partial Least Squares Path Modeling Decision Sciences Partial least squares path modeling (PLS-PM) has become popular in various disciplines to model structural relationships among latent variables measured by manifest variables. To fully benefit from the predictive capabilities ofPLS-PM, researchers must understand the efficacy of predictive metrics used. In this research, we compare the performance of standard PLS-PM criteria and model selection criteria derived from Information Theory, in terms of selecting the best predictive model among a cohort of competing models.
Predictions from PLS Models Emerald Publishing Group Apart from the theoretic explanations offered by our empirical models, practitioners are also interested in the practical implications that they can apply to future cases. Being able to provide predictive diagnoses is an increasingly important issue linking theory and practice, and empirical researchers in hospitality and tourism should heed the call for predictive evaluations of their theoretical models. Fortunately, PLS path models are uniquely suited to predictive analytics. This chapter offers a review of the emerging predictive methodology for PLS path models and an practical guide to what researchers can do today to diagnose the predictive qualities of their models. We follow these discussions with a demonstration on a well regarded model and dataset from the tourism literature.