Search

Structural model assessment in PLS-SEM focuses on evaluating the significance and relevance of path coefficients, followed by the model’s explanatory and predictive power. In this chapter, we discuss the key metrics relevant to structural model assessment in PLS-SEM. We also discuss model comparisons and introduce key criteria for assessing and selecting a model given the data and a set of competing models.

The goal of reflective measurement model assessment is to ensure the reliability and validity of the construct measures and therefore provides support for the suitability of their inclusion in the path model. This chapter introduces the key criteria that are relevant in reflective measurement model assessment: indicator reliability, internal consistency reliability (Cronbach’s alpha, reliability coefficient rhoA, and composite reliability rhoC), convergent validity, and discriminant validity. We illustrate their use by means of the SEMinR package and a well-known model on corporate reputation.

Structural equation modeling is a multivariate data analysis method for analyzing complex relationships among constructs and indicators. To estimate structural equation models, researchers generally draw on two methods: covariance-based SEM (CB-SEM) and partial least squares SEM (PLS-SEM). Whereas CB-SEM is primarily used to confirm theories, PLS represents a causal–predictive approach to SEM that emphasizes prediction in estimating models, whose structures are designed to provide causal explanations. PLS-SEM is also useful for confirming measurement models. This chapter offers a concise overview of PLS-SEM’s key characteristics and discusses the main differences compared to CB-SEM. The chapter also describes considerations when using PLS-SEM and highlights situations that favor its use compared to CB-SEM.

SEMinR is a software package developed for the R statistical environment (R Core Team, 2021). The package includes a user-friendly syntax for creating and estimating structural equation models using estimators such as partial least squares. In this chapter, we introduce the syntax to create, estimate, and report structural equation models using SEMinR. We demonstrate the four steps to specifying and estimating a structural equation model: (1) loading and cleaning the data, (2) specifying the measurement models, (3) specifying the structural model, and (4) estimating, bootstrapping, and summarizing the model. This chapter also describes how to export results and figures from R for professional, publication-quality reporting.

Computational statistics is now an increasingly popular method of analysis for researchers that combines a vast array of algorithms, statistical methods, and the power of functional coding. The R programming language, in particular, has benefitted from this development alongside of traditional graphical user interface (GUI) software. Today, it has become the language of choice for empirical researchers. In this chapter, we introduce the R programming language as well as its popular development environment in the form of RStudio. We walk the reader through downloading both the R language and the RStudio integrated development environment (IDE). Then, we discuss the software layout and demonstrate how to interact with the software. Finally, we address creating and managing R projects and scripts, gaining access to documentation and help via various sources. This chapter is not intended as a tutorial on the writing of code in the R programming language. We do, however, provide useful open-source resources for learning R, which can be accessed from the R console RStudio environment.

PLS-SEM is the preferred approach when formatively specified constructs are included in the PLS path model. In this chapter, we discuss the key steps for evaluating formative measurement models. These include the assessment of (1) convergent validity, (2) indicator collinearity, and (3) statistical significance and relevance of the indicator weights. We introduce key criteria and their thresholds and illustrate their use with an extended version of the corporate reputation model estimated with SEMinR.