Non-symmetrical composite-based path modeling. (English) Zbl 1416.62374

Summary: Partial least squares path modeling presents some inconsistencies in terms of coherence with the predictive directions specified in the inner model (i.e. the path directions), because the directions of the links in the inner model are not taken into account in the iterative algorithm. In fact, the procedure amplifies interdependence among blocks and fails to distinguish between dependent and explanatory blocks. The method proposed in this paper takes into account and respects the specified path directions, with the aim of improving the predictive ability of the model and to maintain the hypothesized theoretical inner model. To highlight its properties, the proposed method is compared to the classical PLS path modeling in terms of explained variability, predictive relevance and interpretation using artificial data through a real data application. A further development of the method allows to treat multi-dimensional blocks in composite-based path modeling.


62H99 Multivariate analysis
Full Text: DOI


[1] Aguirre-Urreta, MI; Marakas, GM, Research notepartial least squares and models with formatively specified endogenous constructs: a cautionary note, Inf Syst Res, 25, 761-778, (2014)
[2] Apel, H.; Wold, H.; Jöreskog, K. (ed.); Wold, H. (ed.), Soft modeling with latent variables in two or more dimensions: PLS estimation and testing for predictive relevance, 209-247, (1982), Amsterdam · Zbl 0503.62065
[3] Becker JM, Arun R, Edward ER (2013) Predictive validity and formative measurement in structural equation modeling: embracing practical relevance. In: Proceedings of the international conference on information systems (ICIS)
[4] Chin, WW; Marcoulides, G. (ed.), The partial least squares approach for structural equation modeling, 295-336, (1998), London
[5] Chin, WW; Esposito Vinzi, V. (ed.); Chin, WW (ed.); Henseler, J. (ed.); Wang, H. (ed.), How to write up and report PLS analyses, 655-690, (2010), Berlin
[6] Dijkstra, Theo K., A perfect match between a model and a mode, 55-80, (2017), Cham
[7] Dolce, P.; Lauro, N., Comparing maximum likelihood and PLS estimates for structural equation modeling with formative blocks, Qual Quant, 49, 891-902, (2015)
[8] Dolce, P.; Esposito Vinzi, V.; Lauro, C.; Abdi, H. (ed.); Esposito Vinzi, V. (ed.); Russolillo, G. (ed.); Saporta, G. (ed.); Trinchera, L. (ed.), Path directions incoherence in pls path modeling: a prediction-oriented solution, (2016), New York · Zbl 1366.62133
[9] Esposito Vinzi, V.; Russolillo, G., Partial least squares algorithms and methods, WIREs Comput Stat, 5, 1-19, (2013)
[10] Evermann, J.; Tate, M., Assessing the predictive performance of structural equation model estimators, J Bus Res, 69, 4565-4582, (2016)
[11] Fornell C, Bookstein FL (1982) Two structural equation models: LISREL and PLS applied to consumer exit-voice theory. J Mark Res 19(4):440-452. http://www.jstor.org/stable/3151718
[12] Fornell, C.; Barclay, DW; Rhee, BD, A model and simple iterative algorithm for redundancy analysis, Multivar Behav Res, 23, 349-360, (1988)
[13] Geisser, S., The predictive sample reuse method with applications, J Am Stat Assoc, 70, 320-328, (1975) · Zbl 0321.62077
[14] Hair, JF; Ringle, CM; Sarstedt, M., PLS-SEM: indeed a silver bullet, J Mark Theory Pract, 19, 139-152, (2011)
[15] Hanafi, M., PLS path modeling: computation of latent variables with the estimation mode B, Comput Stat, 22, 275-292, (2007) · Zbl 1196.62103
[16] Hastie T, Tibshirani R, Friedman J (2009) The elements of statistical learning: data mining, inference, and prediction. Springer, Berlin · Zbl 1273.62005
[17] Henseler, J.; Ringle, C.; Sinkovics, R., The use of partial least squares path modeling in international marketing, Adv Int Mark, 20, 277-319, (2009)
[18] Henseler, J.; Hubona, G.; Ray, PA, Using PLS path modeling in new technology research: updated guidelines, Ind Manag Data Syst, 116, 2-20, (2016)
[19] Höskuldsson, Agnar, Modelling procedures for directed network of data blocks, Chemometrics and Intelligent Laboratory Systems, 97, 3-10, (2009)
[20] Höskuldsson, A., Path regression models and process control optimisation, J Chemom, 28, 235-248, (2014)
[21] Johansson, J., An extension of wollenberg’s redundancy analysis, Psychometrika, 46, 93-103, (1981)
[22] Krämer N (2007) Analysis of high-dimensional data with partial least squares and boosting. Ph.D. thesis, Technische Universität Berlin, Berlin, Germany
[23] Lauro, N.; D’Ambra, L., Non symmetrical exploratory data analysis, Stat Appl, 4, 511-529, (1992)
[24] Lê, S.; Josse, J.; Husson, F., Factominer: a package for multivariate analysis, J Stat Softw, 25, 1-18, (2008)
[25] Lohmöller J (1989) Latent variable path modeling with partial least squares. Physica, Heildelberg · Zbl 0788.62050
[26] Martens H, Naes T (1989) Multivariate calibration. Wiley, Chichester · Zbl 0732.62109
[27] Martens, M.; Tenenhaus, M.; Esposito, V.; Martens, V.; MacFie, H. (ed.), The use of partial least squares methods in new food product development, 492-523, (2007), Cambridge
[28] Næs, T.; Tomic, O.; Mevik, BH; Martens, H., Path modelling by sequential PLS regression, J Chemom, 25, 28-40, (2011)
[29] Pagés, J.; Asselin, C.; Morlat, R.; Robichet, J., L’analyse factorielle multiple dans le traitement des données sensorielles. application à des vins rouges de la vallée de la loire, Sci des Aliments, 7, 549-571, (1987)
[30] R Core Team (2014) R: a language and environment for statistical computing. R foundation for statistical computing, Vienna
[31] Rigdon, EE, Rethinking partial least squares path modeling: in praise of simple methods, Long Range Plan, 45, 341-358, (2012)
[32] Rigdon, EE, Choosing PLS path modeling as analytical method in European management research: a realist perspective, Eur Manag J, (2016)
[33] Ringle, C.; Sarstedt, M.; Straub, D., A critical look at the use of PLS-sem in mis quarterly, MIS Q, 36, 3-14, (2012)
[34] Rönkkö M (2017) Matrixpls: matrix-based partial least squares estimation. https://github.com/mronkko/matrixpls, r package version 1.0.5
[35] Rönkkö, M.; McIntosh, CN; Antonakis, J.; Edwards, JR, Partial least squares path modeling: time for some serious second thoughts, J Oper Manag, 47-48(Complete), 9-27, (2016)
[36] Sarstedt, M.; Ringle, C.; Henseler, J.; Hair, J., On the emancipation of PLS-SEM: a commentary on rigdon (2012), Long Range Plan, 47, 154-160, (2014)
[37] Sarstedt, M.; Hair, JF; Ringle, CM; Thiele, KO; Gudergan, SP, Estimation issues with PLS and cbsem: where the bias lies!, J Bus Res, 69, 3998-4010, (2016)
[38] Shmueli, G.; Ray, S.; Velasquez Estrada, J.; Chatla, S., The elephant in the room: predictive performance of PLS models, J Bus Res, 69, 4552-4564, (2016)
[39] Stone, M., Cross-validatory choice and assessment of statistical predictions, J R Stat Soc, 36, 111-147, (1974) · Zbl 0308.62063
[40] Tenenhaus, M., Component-based structural equation modelling, Total Qual Manag Bus Excell, 19, 871-886, (2008)
[41] Tenenhaus, M.; Hanafi, M.; Esposito Vinzi, V. (ed.); Chin, W. (ed.); Henseler, J. (ed.); Wang, H. (ed.), A bridge between PLS path modeling and multi-block data analysis, (2010), Berlin
[42] Tenenhaus, A.; Tenenhaus, M., Regularized generalized canonical correlation analysis, Psychometrika, 76, 257-284, (2011) · Zbl 1284.62753
[43] Tenenhaus, M.; Vinzi, VE, PLS regression, PLS path modeling and generalized Procrustean analysis: a combined approach for PLS regression, PLS path modeling and generalized multiblock analysis, J Chemom, 19, 145-153, (2005)
[44] Tenenhaus, M.; Esposito, VV; Chatelin, YM; Lauro, C., PLS path modeling, Comput Stat Data Anal, 48, 159-205, (2005) · Zbl 1429.62227
[45] Tucker, L., An inter-battery method of factor analysis, Psychometrika, 23, 111-136, (1958) · Zbl 0097.35102
[46] Vittadini, G.; Minotti, SC; Fattore, M.; Lovaglio, PG, On the relationships among latent variables and residuals in PLS path modeling: the formative-reflective scheme, Comput Stat Data Anal, 51, 5828-5846, (2007) · Zbl 1445.62137
[47] Wertz, C.; Linn, R.; Jöreskog, K., Intraclass reliability estimates: testing structural assumptions, Educ Psychol Meas, 34, 25-33, (1974)
[48] Wold H (1980) Model construction and evaluation when theoretical knowledge is scarce. In: Ramsey JB, Kmenta J (eds) Evaluation of econometric models. Academic Press, pp 47-74
[49] Wold, H.; Jöreskog, K. (ed.); Wold, H. (ed.), Soft modeling: the basic design and some extensions, No. 2, 1-54, (1982), Amsterdam
[50] Wollenberg, AL, Redundancy analysis an alternative for canonical correlation analysis, Psychometrika, 42, 207-219, (1977) · Zbl 0354.92050
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. It attempts to reflect the references listed in the original paper as accurately as possible without claiming the completeness or perfect precision of the matching.