Portal de Periódicos da CAPES

Analysing quadratic effects of formative constructs by means of variance-based structural equation modelling

2011; Palgrave Macmillan; Volume: 21; Issue: 1 Linguagem: Inglês

10.1057/ejis.2011.36

1476-9344

Jörg Henseler, Georg Fassott, Theo K. Dijkstra, Bradley Wilson,

Software Engineering Techniques and Practices

AbstractAbstractTogether with the development of information systems research, there has also been increased interest in non-linear relationships between focal constructs. This article presents six Partial Least Squares-based approaches for estimating formative constructs' quadratic effects. In addition, these approaches' performance is tested by means of a complex Monte Carlo experiment. The experiment reveals significant and substantial differences between the approaches. In general, the performance of the hybrid approach as suggested by Wold (1982) is most convincing in terms of point estimate accuracy, statistical power, and prediction accuracy. The two-stage approach suggested by Chin et al (1996) showed almost the same performance; differences between it and the hybrid approach – although statistically significant – were unsubstantial. Based on these results, the article provides guidelines for the analysis of non-linear effects by means of variance-based structural equation modelling.Keywords: partial least squares path modellingPLSnon-linear effectquadratic effect Additional informationNotes on contributorsJörg HenselerAbout the authorsJörg Henseler is an Associate Professor at the Institute for Management Research, Nijmegen School of Management, Radboud University Nijmegen, The Netherlands, and a Visiting Professor at The Higher Institute of Statistics and Knowledge Management (ISEGI), Universidade Nova de Lisboa, Portugal. His research interests encompass structural equation modelling marketing research, service management, and innovation management. He has published in scholarly journals including Computational Statistics, International Journal of Research in Marketing, and Structural Equation Modeling, and he is editor of two handbooks on partial least squares path modelling.Georg FassottGeorg Fassott is an Associate Professor in the Faculty of Business Studies and Economics at the University of Kaiserslautern, Germany. His research interests are in the areas of e-commerce, entrepreneurial marketing, and structural equation modelling. His recent articles have appeared in journals such as International Journal of Internet Marketing and Advertising, International Marketing Review, Journal of Consumer Behaviour, and Journal of Relationship Marketing.Theo K DijkstraTheo K. Dijkstra is a Professor at the University of Groningen, The Netherlands. He was a Fulbright scholar at the University of California, Department of Psychology. He has published in journals including Econometrica, Psychometrika, The International Economic Review, and the British Journal of Mathematical and Statistical Psychology. He also worked for an institutional asset manager, responsible for the development of decision support tools and portfolio strategies. His research interests include statistical methodology, multivariate statistics, multicriteria decision analysis, and partial least squares.Bradley WilsonBradley Wilson is a Senior Lecturer in the School of Media and Communication, RMIT University, Melbourne, Australia. He has published in the Handbook of Partial Least Squares, Industrial Marketing Management, Sport Marketing Quarterly, International Journal of Sports Marketing and Sponsorship, Public Relations Review and International Journal of Sport Management and Marketing. His research encompasses branding, communication, sponsorship, crises and cause-related marketing often utilising advanced multivariate methods developments.