Ringle, Christian M. and Götz, Oliver and Wetzels, Martin and Wilson, Bradley (2009): On the Use of Formative Measurement Specifications in Structural Equation Modeling: A Monte Carlo Simulation Study to Compare CovarianceBased and Partial Least Squares Model Estimation Methodologies. Published in: Research Memoranda from Maastricht (METEOR)

PDF
MPRA_paper_15390.pdf Download (388kB)  Preview 
Abstract
The broader goal of this paper is to provide social researchers with some analytical guidelines when investigating structural equation models (SEM) with predominantly a formative specification. This research is the first to investigate the robustness and precision of parameter estimates of a formative SEM specification. Two distinctive scenarios (normal and nonnormal data scenarios) are compared with the aid of a Monte Carlo simulation study for various covariancebased structural equation modeling (CBSEM) estimators and various partial least squares path modeling (PLSPM) weighting schemes. Thus, this research is also one of the first to compare CBSEM and PLSPM within the same simulation study. We establish that the maximum likelihood (ML) covariancebased discrepancy function provides accurate and robust parameter estimates for the formative SEM model under investigation when the methodological assumptions are met (e.g., adequate sample size, distributional assumptions, etc.). Under these conditions, MLCBSEM outperforms PLSPM. We also demonstrate that the accuracy and robustness of CBSEM decreases considerably when methodological requirements are violated, whereas PLSPM results remain comparatively robust, e.g. irrespective of the data distribution. These findings are important for researchers and practitioners when having to choose between CBSEM and PLSPM methodologies to estimate formative SEM in their particular research situation.
Item Type:  MPRA Paper 

Original Title:  On the Use of Formative Measurement Specifications in Structural Equation Modeling: A Monte Carlo Simulation Study to Compare CovarianceBased and Partial Least Squares Model Estimation Methodologies 
Language:  English 
Keywords:  PLS, path modeling, covariance structure analysis, structural equation modeling, formative measurement, simulation study 
Subjects:  C  Mathematical and Quantitative Methods > C1  Econometric and Statistical Methods and Methodology: General > C10  General C  Mathematical and Quantitative Methods > C5  Econometric Modeling > C51  Model Construction and Estimation C  Mathematical and Quantitative Methods > C3  Multiple or Simultaneous Equation Models ; Multiple Variables > C30  General C  Mathematical and Quantitative Methods > C1  Econometric and Statistical Methods and Methodology: General > C15  Statistical Simulation Methods: General 
Item ID:  15390 
Depositing User:  Christian M. Ringle 
Date Deposited:  25. May 2009 09:41 
Last Modified:  14. Feb 2013 14:14 
References:  Blalock, H. M. (1971). Causal models involving unmeasured variables in stimulusresponse situations. In H. M. Blalock (Ed.), Causal models in the social science (pp. 335347). Chicago, New York: Aldine Atherton. Bollen, K. A. (1989). Structural equations with latent variables. New York: Wiley. Bollen, K. A., & Lennox, R. (1991). Conventional wisdom on measurement: A structural equation perspective. Psychological Bulletin, 110(2), 305314. Boomsma, A. (1983). On the robustness of LISREL (maximum likelihood estimation against small sample size and nonnormality). Doctoral dissertation, University of Groningen, The Netherlands. Amsterdam: Sociometric Research Foundation. Boomsma, A. (2000). Reporting on structural equation analyses. Structural Equation Modeling: A Multidisciplinary Journal, 7(3), 461483. Boomsma, A., & Hoogland, J. J. (2001). The robustness of LISREL modeling revisited. In R. Cudeck, S. du Toit & D. Sörbom (Eds.), Structural equation modeling: Present and future (pp. 139168). Chicago: Scientific Software International. Browne, M. W. (1984). Asymptotically distributionfree methods for the analysis of covariance structures. British Journal of Mathematical and Statistical Psychology, 37, 6283. Cassel, C. M., Hackl, P., & Westlund, A. H. (1999). Robustness of partial leastsquares method for estimating latent variable quality structures. Journal of Applied Statistics, 26(4), 435446. Chin, W. W. (1998). The partial least squares approach to structural equation modeling. In G. A. Marcoulides (Ed.), Modern methods for business research (pp. 295358). Mahwah: Lawrence Erlbaum. Chin, W. W., Marcolin, B. L., & Newsted, P. R. (2003). A partial least squares latent variable modeling approach for measuring interaction effects: Results from a Monte Carlo simulation study and an electronicmail emotion / adoption study. Information Systems Research, 14(2), 189217. Curran, P. J., Bollen, K. A., Paxton, P., Kirby, J., & Chen, F. (2002). The noncentral chisquare distribution in misspecified structural equation models: Finite sample results from a Monte Carlo simulation. Multivariate Behavioral Research, 37(1), 136. Diamantopoulos, A. (2006). The error term in formative measurement models: Interpretation and modeling implications. Journal of Modelling in Management, 1, 717. Diamantopoulos, A., & Winklhofer, H. M. (2001). Index construction with formative indicators: An alternative to scale development. Journal of Marketing Research, 38, 269277. Edwards, J. R., & Bagozzi, R. P. (2000). On the nature and direction of relationships between constructs and measures. Psychological Methods, 5(2), 155174. Fleishman, A. I. (1978). A method for simulating nonnormal distributions. Psychometrika, 43(4), 521532. Fornell, C., & Bookstein, F. L. (1982). Two structural equation models: LISREL and PLS applied to consumer exitvoice theory. Journal of Marketing Research, 440452. Hsu, H.H., Chen, W.H., & Hsieh, M.J. (2006). Robustness testing of PLS, LISREL, EQS and ANNbased SEM for measuring customer satisfaction. Total Quality Management and Business Excellence, 17(3), 355372. Hu, L.T., & Bentler, P. M. (1999). Cutoff criteria for fit indices in covariance structure analysis: Conventional criteria versus new alternatives. Structural Equation Modeling: A Multidisciplinary Journal, 6(1), 155. Jarvis, C. B., MacKenzie, S., B., & Podsakoff, P., M. (2003). A critical review of construct indicators and measurement model misspecification in marketing and consumer research. Journal of Consumer Research, 30(2), 199218. Jöreskog, K. G., & Goldberger, A. S. (1975). Estimation of a model with multiple indicators and multiple causes of a single latent variable. Journal of the American Statistical Association, 70(351), 631639. Jöreskog, K. G., & Sörbom, D. (2001). LISREL 8. User’s reference guide. Lincolnwood: Scientific Software International. Jöreskog, K. G. & Wold, H. (1982). The ML and PLS technique for modeling with latent variables: Historical and comparative aspects. In K. G. Jöreskog & H. Wold (Eds.), Systems under indirect observation, part I (pp. 263270). Amsterdam, New York, Oxford: NorthHolland. Lee, D. Y., & Tsang, E. W. K. (2001). The effects of entrepreneurial personality, background and network activities on venture growth. Journal of Management Studies, 38(4), 583603. Lohmöller, J.B. (1989). Latent variable path modeling with partial least squares. Heidelberg: Physica. MacCallum, R. C., & Browne, M. W. (1993). The use of causal indicators in covariance structure models: Some practical issues. Psychological Bulletin, 114(3), 533541. Marcoulides, G. A., & Hershberger, S. L. (1997). Multivariate statistical methods: a first course. Mahwah: Lawrence Erlbaum Associates. Marcoulides, G. A., & Saunders, C. (2006). PLS: A silver bullet? MIS Quarterly, 30(2), IIIIV. McDonald, R. P. (1996). Path analysis with composite variables. Multivariate Behavioral Research, 31(2), 239270. Micceri, T. (1989). The unicorn, the normal curve, and other improbable creatures. Psychological Bulletin, 105(1), 156166. Nunnally, J. C., & Bernstein, I. H. (1994). Psychometric theory (3rd ed.). New York: McGrawHill. Paxton, P., Curran, P. J., Bollen, K. A., Kirby, J., & Chen, F. (2001). Monte Carlo experiments: Design and implementation. Structural Equation Modeling: A Multidisciplinary Journal, 8(2), 287312. Reinartz, W. J., Echambadi, R., & Chin, W. W. (2002). Generating nonnormal data for simulation of structural equation models using Mattson's method. Multivariate Behavioral Research, 37(2), 227244. Rigdon, E. E. (1995). A necessary and sufficient identification rule for structural models estimated in practice. Multivariate Behavioral Research, 30(3), 359384. Rigdon, E. E. (1998). Structural equation modeling. In G. A. Marcoulides (Ed.), Modern methods for business research (pp. 251294). Mahwah: Lawrence Erlbaum. Ringle, C. M., Wende, S., & Will, A. (2005). SmartPLS 2.0. Hamburg: University of Hamburg. Satorra, A. (1990). Robustness issues in structural equation modeling: a review of recent developments. Quality and Quantity, 24(4), 367386. Satorra, A., & Bentler, P. M. (2001). A scaled difference chisquare test statistic for moment structure analysis. Psychometrika, 66(4), 507514. Schneeweiß, H. (1991). Models with latent variables: LISREL versus PLS. Statistica Neerlandica, 45(1), 145157. StatSoft. (2005). STATISTICA for windows version 7.1. Tulsa: StatSoft. Stephenson, M., T., & Holbert, R. L. (2003). A Monte Carlo simulation of observable versus latent variable structural equation modeling techniques. Communication Research, 30(3), 332354. Tenenhaus, M., Esposito Vinzi, V., Chatelin, Y.M., & Lauro, C. (2005). PLS path modeling. Computational Statistics & Data Analysis, 48(1), 159205. Thatcher, J. B., Stepina, L. P., & Boyle, R. J. Turnover of information technology workers: Examining empirically the influence of attitudes, job characteristics, and external markets. Journal of Management Information Systems, 19(3), 231261. Vale, C. D., & Maurelli, V. A. (1983). Simulating multivariate nonnormal distributions. Psychometrika, 48(3), 465471. Westlund, A., H., Cassel, C., M., Eklof, J., & Hackl, P. (2001). Structural analysis and measurement of customer perceptions, assuming measurement and specifications errors. Total Quality Management, 12(7,8), 873881. Williams, L. J., Edwards, J. R., & Vandenberg, R. J. (2003). Recent advances in causal modeling methods for organizational and management research. Journal of Management, 29(6), 903936. Wixom, B. H., & Watson, H. J. (2001). An empirical investigation of the factors affecting data warehousing success. MIS Quarterly, 25(1), 1741. Wold, H. (1973). Nonlinear iterative partial least squares (NIPALS) modeling: Some current developments. In P. R. Krishnaiah (Ed.), Proceedings of the Third International Symposium on Multivariate Analysis (pp. 383407). Dayton, OH. Wold, H. (1974). Causal flows with latent variables: Parting of the ways in the light of NIPALS modeling. European Economic Review, 5(1), 6786. Wold, H. (1980). Model construction and evaluation when theoretical knowledge is scarce: Theory and application of partial least squares. In J. Kmenta & J. Ramsey (Eds.), Evaluation of econometric models (pp. 4774). London: Academic Press. Wold, H. (1982a). Soft modeling: The basic design and some extensions. In K. G. Jöreskog & H. Wold (Eds.), Systems under indirect observation, part II (pp. 154). Amsterdam, New York, Oxford: NorthHolland. Wold, H. (1982b). Systems under indirect observation using PLS. In C. Fornell (Ed.), A second generation of multivariate analysis, vol. 1 (pp. 325347). New York: Praeger. 
URI:  https://mpra.ub.unimuenchen.de/id/eprint/15390 