It has been almost a decade since the first edition of our book was published in 2014. In that period of time, the field of structural equation modeling (SEM), and particularly partial least squares structural equation modeling (PLS-SEM), has changed considerably. While some traditional statistical methods have continued to evolve and extend their capabilities, PLS-SEM has expanded rapidly to include numerous additional analytical options. Much of the focus has been on the development of methods for confirming the quality of composite measures as representations of theoretical concepts (using procedures similar to the traditional confirmatory factor analysis in common factor models) and for assessing a model’s out-of-sample predictive power. But many somewhat smaller analytical improvements have emerged as well.

When we wrote the first and second editions, we were confident that interest in PLS-SEM would increase. But even our wildest expectations were exceeded. We never anticipated that the interest in the PLS-SEM method would literally explode in a few years! The two previous editions of our book have been cited more than 25,000 times according to Google Scholar, and the books have been translated into seven other languages, including German, Italian, and Spanish. Furthermore, the book now also comes in an R software edition (Hair et al, 2022). A Primer on Partial Least Squares Structural Equation Modeling (PLS-SEM) has been the premier text in the field of PLS-SEM for many years, and based on the advances included in this new edition, we are confident it will remain the leading text in the future.

A review of major social sciences journals clearly demonstrates that applications of PLS-SEM have grown exponentially in the past decade, as evidenced in the popularity of the terms “PLS-SEM” and “PLS path modeling” in the Web of Science database (Exhibit 1). Two journal articles published by our author team before the first edition also provide clear evidence of the popularity of PLS-SEM. The two articles have been the most widely cited in those journals since their publication—our 2012 article in the Journal of Academy of Marketing Science, “An assessment of the use of partial least squares structural equation modeling in marketing research,” cited over 5,000 times according to Google Scholar, has been the number one highest impact article published in the top 20 marketing journals, according to Shugan’s list of most cited marketing articles (Volume 2, Issue 3). It has also been awarded the 2015 Emerald Citations of Excellence award. Moreover, our 2011 article in the Journal of Marketing Theory and Practice, “PLS-SEM: Indeed a silver bullet,” has surpassed the 10,000 citations mark. More recently, our 2015 Journal of the Academy of Marketing Science article “A new criterion for assessing discriminant validity in variance-based structural equation modeling” was ranked as the top economic article in the Thompson Reuters Essential Science Indicators Ranking, which ranks it in the top 0.1% most cited research articles worldwide.

Exhibit 1: Number of PLS-SEM-related articles per year

Note: Number of articles returned from the Web of Science database for the search terms "partial least squares structural equation modeling," “PLS-SEM,” and “PLS path modeling."

 

 PLS-SEM has also enjoyed increasingly widespread interest among methods researchers. A rapidly growing number of scholars have gained interest in PLS-SEM, and they complement the initial core group of authors that have shaped the method (Khan et al., 2019). Their research papers offer novel perspectives on the method, sometimes sparking significant debates. Prominent examples include the rejoinders to Rigdon’s (2012) Long Range Planning article by Bentler and Huang (2014), Dijkstra (2014), Sarstedt, Ringle, Henseler, and Hair (2014), and Rigdon (2014) himself. Under the general theme “rethinking partial least squares path modeling,” this exchange of thoughts offered the point of departure for some of the most important PLS-SEM developments in the last few years. Other articles have further clarified the similarities and differences between PLS-SEM and covariance-based SEM, which has long been viewed as the default method for analyzing causal models. For example, Hair, Hult, Ringle, Sarstedt, and Thiele (2017) and Sarstedt, Hair, Ringle, Thiele, and Gudergan (2016) discuss the measurement philosophies underlying the two SEM methods and demonstrate the biases that occur when using PLS-SEM and covariance-based SEM on models, which are inconsistent with what the methods assume. Related to this debate, Rigdon, Sarstedt, and Ringle (2017) argue how differences in philosophy of science and different expectations about the research situation tend to induce a preference for one method over the other (see also Hair & Sarstedt, 2019). Similar discussions have emerged in psychology where researchers increasingly acknowledge that reducing measurement to only the philosophy assumed by covariance-based SEM (CB-SEM) is a very restrictive view, which does not apply to nearly all constructs (Rhemtulla, van Bork, & Borsboom, 2020).

Shmueli, Ray, Velasquez Estrada, and Chatla (2016) have made a substantial contribution to the field by shifting researchers’ focus to the assessment of PLS path models’ predictive power. Bemoaning the emphasis of explanatory model assessment in applications of PLS-SEM, the authors introduced the PLSpredict procedure, which allows for evaluating a model’s out-of-sample predictive power. Their research has sparked a series of follow-up studies, offering guidelines on how to use PLSpredict (Shmueli et al., 2019) and introducing tests that allow comparing different models in terms of their predictive power (Liengaard et al., 2020).

Finally, Rönkkö and Evermann’s (2013) critique of the PLS-SEM method in Organizational Research Methods offered an excellent opportunity to show how uninformed and blind criticism of the PLS-SEM method leads to misleading, incorrect, and false conclusions (see the rejoinder by Henseler et al., 2014). While this debate also nurtured some advances in PLS-SEM (Rönkkö and Evermann 2013)—such as the new heterotrait-monotrait (HTMT) criterion to assess discriminant validity (Franke & Sarstedt, 2019; Henseler, Ringle, & Sarstedt, 2015)—we believe it is important to reemphasize our previous call: “Any extreme position that (often systematically) neglects the beneficial features of the other technique and may result in prejudiced boycott calls […], is not good research practice and does not help to truly advance our understanding of methods (or any other research subject)” (Hair, Ringle, & Sarstedt, 2012, p. 313; see also Petter, 2018; Sarstedt, Ringle, Henseler, & Hair, 2014).

Enhancement of the methodological foundations of the PLS-SEM method has been accompanied by the release of multiple new versions of SmartPLS 3 (Ringle, Wende, & Becker, 2015), which implement most of these latest extensions in this very user-friendly software. These updates are much more than just a simple revision. They incorporate a broad range of new algorithms and major new features that previously were not available or had to be executed manually (Sarstedt & Cheah, 2019). In light of the developments in terms of the much more widespread utilization of PLS-SEM, and further enhancements and extensions of the method and software support, a new edition of the book is clearly timely and warranted.

While there are numerous published articles on the method, until our first two editions and even today, there are very few other comprehensive books that explain the fundamental aspects of the method, particularly in a way that can be understood by individuals with limited statistical and mathematical training. This third edition of our book updates and extends the coverage of PLS-SEM for social sciences researchers and creates awareness of the most recent developments in an analytical tool that will enable scholars and practitioners to pursue research opportunities in many new and different ways.

The approach of this book is based on the authors’ many years of conducting and teaching research, as well as the desire to communicate the fundamentals of the PLS-SEM method to a much broader audience. To accomplish this goal, we have limited the emphasis on equations, formulas, Greek symbols, and so forth that are typical of most books and articles. Instead, we explain in detail the basic fundamentals of PLS-SEM and provide rules of thumb that can be used as general guidelines for understanding and evaluating the results of applying the method. We also rely on a single software package (SmartPLS 3) that can be used not only to complete the exercises in this book but also in the reader’s own research.

As a further effort to facilitate learning, we use a single case study throughout the book. The case is drawn from a published study on corporate reputation and we believe it is general enough to be understood by many different areas of social science research, thus further facilitating comprehension of the method. Review and critical thinking questions are posed at the end of the chapters, and key terms are defined to better understand the concepts. Finally, suggested readings and extensive references are provided to enhance more advanced coverage of the topic.

We are excited to share with you the many new topics we have included in this edition. These include the following:

• An overview of the latest research on the nature of composite-based modeling, which is the conceptual foundation for PLS-SEM.
• More on the distinction between PLS-SEM and CB-SEM and the model constellations, which are favorable toward the use of PLS-SEM.
• Application of PLS-SEM with secondary (archival) data.
• Information on how to treat control variables in PLS path models.
• Extended discussion of model fit in PLS-SEM.
• Further coverage of internal consistency reliability using and inference testing in discriminant validity assessment.
• Enhanced guidelines for generating and validating single-item measures for redundancy analyses.
• Improved guidelines for determining minimum sample sizes using the inverse square root method.
• Coverage of the weighted PLS-SEM algorithm.
• Latest research on bootstrapping settings and assessment.
• Analyzing a model’s out-of-sample predictive power using the PLSpredict procedure.
• Metrics for model comparisons and selection (e.g., the Bayesian information criterion), including cross-validation of alternative models.
• Revision and extension of the chapter on mediation, which now covers more types of mediation, including multiple mediation, and demonstrates why PLS-SEM is superior to the PROCESS-based mediation analyses.
• Explanation and guidelines on moderated mediation.
• Latest research on specifying and estimating higher-order constructs.
• Updated recommendations for multigroup analysis.
• Extended coverage of advanced concepts and methods such as necessary condition analysis and endogeneity.
• Coverage of the latest literature on PLS-SEM.

All examples in the edition are updated using the newest version of the most widely applied PLS-SEM software—SmartPLS 3. The book chapters and learning support supplements are organized around the learning outcomes shown at the beginning of each chapter. Moreover, instead of a single summary at the end of each chapter, we present a separate concise summary for each learning outcome. This approach makes the book more understandable and usable for both students and teachers. The PLS-SEM-Academy offers video-based online courses based on this book and its earlier editions, but also on advanced PLS-SEM topics following the explanations of Hair, Sarstedt, Ringle and Gudergan (2018).

 

We would like to acknowledge the many insights and suggestions provided by the reviewers: Maxwell K. Hsu (University of Wisconsin), Toni M. Somers (Wayne State University), and Lea Witta (University of Central Florida), as well as a number of our colleagues and students. Most notably, we thank Jan-Michael Becker (BI Norwegian Business School), Zakariya Belkhamza (Ahmed Bin Mohammed Military College), Charla Brown (Troy University), Roger Calantone (Michigan State University), Fabio Cassia (University of Verona), Gabriel Cepeda Carrión (University of Seville), Jacky Jun Hwa Cheah (Universiti Putra Malaysia), Nicholas Danks (Trinity College Dublin), Adamantios Diamantopoulos (University of Vienna), Markus Eberl (Kantar), George Franke (University of Alabama), Anne Gottfried (University of Texas, Arlington), Siegfried P. Gudergan (University of Waikato), Saurabh Gupta (Kennesaw State University), Karl-Werner Hansmann (University of Hamburg), Dana Harrison (East Tennessee State University), Sven Hauff (Helmut Schmidt University), Mike Hollingsworth (Old Dominion University), Philip Holmes (Pensacola Christian College), Chris Hopkins (Auburn University), Lucas Hopkins (Florida State University), Heungsun Hwang (McGill University), Ida Rosnita Ismail (Universiti Kebangsaan Malaysia), April Kemp (Southeastern Louisiana University), David Ketchen (Auburn University), Ned Kock (Texas A&M University), Marcel Lichters (TU Chemnitz), Benjamin Liengaard (Aarhus Universitet), Chein-Hsin Lin (Da-Yeh University), Yide Liu (Macau University of Science and Technology), Francesca Magno (University of Bergamo), Lucy Matthews (Middle Tennessee State University), Jay Memmott (University of South Dakota), Mumtaz Ali Memon (NUST Business School), Adam Merkle (University of South Alabama), Ovidiu I. Moisescu (Babeș-Bolyai University), Zach Moore (University of Louisiana at Monroe), Arthur Money (Henley Business School), Christian Nitzl (Universität der Bundeswehr München), Torsten Pieper (University of North Carolina), Lacramioara Radomir (Babeș-Bolyai University), Arun Rai (Georgia State University), Sascha Raithel (Freie Universität Berlin), S. Mostafa Rasoolimanesh (Taylor’s University), Soumya Ray (National Tsing Hua University), Nicole Richter (University of Southern Denmark), Edward E. Rigdon (Georgia State University), Jeff Risher (Southeastern Oklahoma University), José Luis Roldán (University of Seville), Phillip Samouel (University of Kingston), Amit Saini (University of Nebraska-Lincoln), Francesco Scafarto (University of Rome “Tor Vergata”), Bruno Schivinski (University of London), Rainer Schlittgen (University of Hamburg), Manfred Schwaiger (Ludwig-Maxmillians-University Munich), Pratyush N. Sharma (University of Alabama), Wen-Lung Shiau (Zhejiang University of Technology), Galit Shmueli (National Tsing Hua University), Donna Smith (Ryerson University), Detmar W. Straub (Georgia State University), Hiram Ting (UCSI University), Ron Tsang (Agnes Scott College), Ramayah Thurasamy (Universiti Sains Malaysia), Huiwen Wang (Beihang University), Sven Wende (SmartPLS GmbH), Ronald Tsang (Agnes Scott College), and Anita Whiting (Clayton State University) for their helpful remarks.

Also, we thank the team of doctoral students and research fellows at Hamburg University of Technology and Otto-von-Guericke-University Magdeburg—namely, Susanne Adler, Michael Canty, Svenja Damberg, Zita K. Eggardt, Lena Frömbling, Frauke Kühn, Benjamin Maas, Mandy Pick, and Martina Schöniger—for their kind support. In addition, at SAGE we thank Leah Fargotstein for her support and great work. We hope this book will expand knowledge of the capabilities and benefits of PLS-SEM to a much broader group of researchers and practitioners. Last, if you have any remarks, suggestions, or ideas to improve this book, please get in touch with us. We appreciate any feedback on the book’s concept and contents!

 

Joseph F. Hair, Jr.

University of South Alabama

 

G. Tomas M. Hult

Michigan State University

 

Christian M. Ringle

Hamburg University of Technology, Germany

and University of Waikato, New Zealand

 

Marko Sarstedt

Otto-von-Guericke University, Magdeburg, Germany

and Babeș-Bolyai University, Romania