Partial least squares structural equation modeling (PLS-SEM)

Abstract

Purpose – The authors aim to present partial least squares (PLS) as an evolving approach to structural equation modeling (SEM), highlight its advantages and limitations and provide an overview of recent research on the method across various fields. Design/methodology/approach – In this review article, the authors merge literatures from the marketing, management, and management information systems fields to present the state-of-the art of PLS-SEM research. Furthermore, the authors meta-analyze recent review studies to shed light on popular reasons for PLS-SEM usage. Findings – PLS-SEM has experienced increasing dissemination in a variety of fields in recent years with nonnormal data, small sample sizes and the use of formative indicators being the most prominent reasons for its application. Recent methodological research has extended PLS-SEM's methodological toolbox to accommodate more complex model structures or handle data inadequacies such as heterogeneity. Research limitations/implications – While research on the PLS-SEM method has gained momentum during the last decade, there are ample research opportunities on subjects such as mediation or multigroup analysis, which warrant further attention. Originality/value – This article provides an introduction to PLS-SEM for researchers that have not yet been exposed to the method. The article is the first to meta-analyze reasons for PLS-SEM usage across the marketing, management, and management information systems fields. The cross-disciplinary review of recent research on the PLS-SEM method also makes this article useful for researchers interested in advanced concepts.

Impacts of the CSR strategies of technology companies on performance and competitiveness

“…Since SmartPLS is an model estimation and SEM analysis programme, the estimation process used two steps to evaluate the outer and inner models (Hair, Sarstedt, Hopkins & Kuppelwieser, 2014). First, the measurement model of the relationships between the indicators and constructs was determined (Roldán & Sánchez-Franco, 2012).…”

Absorptive capacity and innovation in low-tech companies in emerging economies

“…According to Hair et al (2014), mediation represents a situation in which a mediating variable to some extent absorbs the effect of an exogenous construct (with independent variables) in an endogenous construct (with the dependent variable) in the PLS path model. The evaluation of variance accounted for (VAF) determines to what extent the mediation process explains the variance of the dependent variable.…”

“…Table 4 shows the coefficients and p value of the research model under study. To generate statistical significance in the hypotheses, according to Hair, Sarstedt, Hopkins, & Kuppelwieser (2014), the bootstrapping technique is used, with 1000 re-samples. The direct effects are positive and significant.…”

The Key Determinants of Leadership Performance Effectiveness in Public Research and Comprehensive Universities: An Advanced PLS-Sem Study in Malaysian Context

“… Undertaking further analysis to check whether the differences between the path coefficients in the models resulted from FIMIX-PLS were significant using the procedure proposed by Henseler, Ringle, and Sarstedt (2016).  Performing Partial Least Squares Multi Group Analysis (PLS-MGA) in order to compare different groups as suggested by Hair, Hult et al (2014) and Hair, Sarstedt, Hopkins, andKuppelwieser (2014).…”