Topic: Identifying Model Misspecification in PLS

Speaker: Jörg Evermann [Website]

Affiliation: Memorial University of Newfoundland

Abstract:

Partial Least Squares (PLS) is a statistical technique that is widely used in the Information Systems discipline to estimate statistical models with structural equations and latent variables. While PLS does not provide a statistical test of model fit to data, its proponents have suggested a set of criteria that good PLS models should fulfill.

Conversely, when a model does not satisfy these criteria, it would be judged a bad model. In this paper, we report on the results of a simulation study to examine to what extent the proposed model quality criteria are able to identify misspecified models.

About Jörg Evermann:

Joerg Evermann is an associate professor of Information Systems with the Faculty of Business Administration at Memorial University of Newfoundland, in St. John's, Canada. He received his Diplom Wirt.-Inf. from the University of Muenster. After receiving his PhD from the University of British Columbia, he was a lecturer with Victoria University in Wellington, New Zealand, before returning to Canada.

Joerg's interests are in conceptual modeling, database integration, and research methods in information systems. Joerg has over 40 peer reviewed publications and his work has appeared in leading international journals such as Information Systems Journal, Information Systems, IEEE Transactions on Knowledge and Data Engineering, and IEEE Transactions on Software Engineering. His work on structural equation modeling has been presented at ICIS, the premier international conference on information systems, and published in the journal SEM - A Multidisciplinary Journal.