Abstract Variance-based SEM, also known under the term partial least squares (PLS) analysis, is an approach that has gained increasing interest among marketing researchers in recent years. During the last… Click to show full abstract
Abstract Variance-based SEM, also known under the term partial least squares (PLS) analysis, is an approach that has gained increasing interest among marketing researchers in recent years. During the last 25 years, more than 30 articles have been published in leading marketing journals that have applied this approach instead of the more traditional alternative of covariance-based SEM (CBSEM). However, although an analysis of these previous publications shows that there seems to be at least an implicit agreement about the factors that should drive the choice between PLS analysis and CBSEM, no research has until now empirically compared the performance of these approaches given a set of different conditions. Our study addresses this open question by conducting a large-scale Monte-Carlo simulation. We show that justifying the choice of PLS due to a lack of assumptions regarding indicator distribution and measurement scale is often inappropriate, as CBSEM proves extremely robust with respect to violations of its underlying distributional assumptions. Additionally, CBSEM clearly outperforms PLS in terms of parameter consistency and is preferable in terms of parameter accuracy as long as the sample size exceeds a certain threshold (250 observations). Nevertheless, PLS analysis should be preferred when the emphasis is on prediction and theory development, as the statistical power of PLS is always larger than or equal to that of CBSEM; already, 100 observations can be sufficient to achieve acceptable levels of statistical power given a certain quality of the measurement model. Selection Procedure The Jan-Benedict E.M. Steenkamp Award for Long-Term Impact is given annually to papers published in IJRM in recognition of their exceptional contributions to academic marketing research by demonstrating long-term impact. A 4-member Award Committee, formed by the IJRM Editor-in-Chief (PK Kannan) and Co-Editor (Iris W. Hung), managed the nomination and selection procedure. For 2020, the committee was composed of Praveen Kopalle, chairperson (Dartmouth College, USA), Ujwal Kayande (Melbourne Business School, Australia), Sharon Ng (Nanyang Technological University, Singapore), and Alina Sorescu (Texas AM self-voting was not allowed.) The eleven (11) papers that received the most votes in the first round made up the ballot for the second and final round of voting in which the Editorial Board could choose only 1 paper. (This year there were 11 instead of 10 papers due to a tie for the 10th place.) 2. After receiving the votes, the Award Committee deliberated on the winning paper guided by the following criteria: (1) the votes received from the IJRM Editorial Board from the two rounds of voting, (2) its ISI and Google Scholar citations, and (3) its quality, as assessed by the committee's in-depth reading. There can be two winners in exceptional cases (not more than once every 3 years on average). Statement from the Award Committee During the past two decades, there has been a renewed interest among researchers to use partial least squares analysis (PLS). However, prior research has not evaluated the relative performance of covariance- based structural equation modeling (CBSEM) and PLS approaches per a set of key characteristics such as sample size, number of indicators per construct, distributional assumptions etc. An interesting and important question is whether we can arrive at a set of rules that researchers may use in their choice of CBSEM versus PLS. The paper by Reinartz, Haenlein, and Henseler explores this issue and examines whether each of the approaches converge to a proper solution, the degree of parameter accuracy between the approaches, the relative importance of the different design factors on parameter accuracy, statistical power etc. The authors conduct a set of Monte Carlo simulations based on 240 scenarios defined by a full factorial design of four design factors. The results suggest that the statistical power of PLS is always larger than or equal to that of maximum likelihood-based CBSEM. Further, their simulations show that PLS can be a very good methodological choice if sample size is low. Finally, their results indicate that CBSEM is actually extremely robust to violations of its underlying distributional assumptions. This paper led by a clear margin by receiving the most votes of the IJRM Editorial Board and was approved unanimously by the award committee. In addition, the evidence of its impact is highlighted by 1039 Web of Science and 2320 Google Scholar citations, which makes it the best cited paper among all the initial round award nominees and shows its consistent use by scholars to decide which method to use. We congratulate the authors for receiving this award. The 2021 Award Committee: Praveen Kopalle, chairperson, Ujwal Kayande, Sharon Ng, and Alina Sorescu 11 Shortlisted papers: • Will the frog change into a prince? Predicting future customer profitability. Roland T. Rust, V. Kumar, Rajkumar Venkatesan. Pages 281-294, Vol 28 (4) • Agent-Based Modeling in Marketing: Guidelines for Rigor. William Rand and Roland T. Rust. Pages 181-193, Vol 28 (3) • Generalizations on consumer innovation adoption: A meta-analysis on drivers of intention and behavior. Joep W.C. Arts, Ruud T. Frambach, Tammo H.A. Bijmolt. Pages 134-144, Vol 28 (2) • Innovation diffusion and new product growth models: A critical review and research directions. Renana Peres, Eitan Muller, Vijay Mahajan. Pages 91-106, Vol 27 (2) • The chilling effects of network externalities. Jacob Goldenberg, Barak Libai, Eitan Muller. Pages 4-15, Vol 27 (1) • An empirical comparison of the efficacy of covariance-based and variance-based SEM. Werner Reinartz, Michael Haenlein, Jorg Henseler. Pages 332-344, Vol 26 (4) • A new measure of brand personality. Maggie Geuens, Bert Weijters, Kristof De Wulf. Pages 97-107, Vol 26 (2) • Measuring the impact of positive and negative word of mouth on brand purchase probability. Robert East, Kathy Hammond, Wendy Lomax. Pages 215–224, Vol 25 (3) • Reaping relational rewards from corporate social responsibility: The role of competitive positioning. Shuili Du, C.B. Bhattacharya, Sankar Sen. Pages 224-241, Vol 24 (3) • The NPV of bad news. Jacob Goldenberg, Barak Libai, Sarit Moldovan, Eitan Muller. Pages 186–200, Vol 24 (3) • Antecedents and purchase consequences of customer participation in small group brand communities. Richard P. Bagozzi, Utpal M. Dholakia. Pages 45-61, Vol 23 (1)
               
Click one of the above tabs to view related content.