PLS SEM, a quantitative methodology to test theoretical models from library and information science

Abstract

Structural equation modeling (SEM), with the technique of partial least squares (PLS), can be used for exploratory and predictive evaluations of the causal relationships and impact among variables postulated in theoretical models. This work presents PLS-SEM’s basic notions as a useful methodology to validate the abundance of models in the library and information science field; it offers an example of its application to test a model for measuring the impact of information resources and services on Mexican universities’ academic competitiveness; and it proposes its application to test the Information Needs Model.