×

Likelihood and PLS estimators for structural equation modeling: an assessment of sample size, skewness and model misspecification effects. (English) Zbl 1402.62342

Lita da Silva, João (ed.) et al., Advances in regression, survival analysis, extreme values, Markov processes and other statistical applications. Selected papers based on the presentations of the 17th congress of the Portuguese Statistical Society, Sesimbra, Portugal, September 30–October 3, 2009. Berlin: Springer (ISBN 978-3-642-34903-4/hbk; 978-3-642-34904-1/ebook). Studies in Theoretical and Applied Statistics. Selected Papers of the Statistical Societies, 11-33 (2013).
Summary: This chapter aims to contribute to a better understanding of partial least squares (PLS) and maximum likelihood (ML) estimators’ properties, through the comparison and evaluation of these estimation methods for structural equation models with latent variables based on customer satisfaction data. Although PLS is a well-established tool to estimate structural equation models, more work is still needed in order to better understand its properties and relative merits when compared to likelihood methods. Despite the controversy over these two estimation techniques, their complexity makes any analytical comparison very difficult to be made. Therefore, it constitutes a fertile ground for conducting simulation studies. This chapter continues the authors’ research with M. H. Almeida [“Comparison of likelihood and PLS estimators for structural equation modelling: a simulation with customer satisfaction data”, in: Handbook of partial least squares. Concepts, methods and applications. Berlin, Heidelberg: Springer. 289–307 (2010; doi:10.1007/978-3-540-32827-8_14)], which has compared PLS and ML estimators using Monte Carlo simulation within three different frameworks (symmetric data, skewed data and formative blocks). It also continues to generate the data according to the ECSI (European Customer Satisfaction Index) model with the assumption that the coefficients of the structural and measurement models are known. This new chapter introduces the effect of sample size and includes two different simulations. The first one is conducted in a context of both symmetric data and skewed response data. This simulation is conducted for the sample sizes \(n=50\), 100, 150, 250, 500, 1,000 and 2,000 and uses reflective blocks. A second simulation includes the presence of model misspecifications (omissions of an existent path) for a sample size of 250 observations and symmetric data. In all simulations the ability of each method to adequately estimate the inner model coefficients and indicator loadings is evaluated. The estimators are analysed in terms of bias and dispersion (standard deviation). Results have shown that overall PLS estimates are generally better than covariance-based estimates. This is particularly true when the data is asymmetric, when estimating the model for smaller sample sizes and for the inner model structure.
For the entire collection see [Zbl 1270.62010].

MSC:

62P20 Applications of statistics to economics
62G05 Nonparametric estimation
62J05 Linear regression; mixed models
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] Bollen, K.A.: Structural Equations with Latent Variables. Wiley, New York (1989) · Zbl 0731.62159
[2] Cassel, C., Hackl, P., Westlund, A.: On measurement of intangibles assets: a study of robustness of partial least squares. Total Qual. Manag. 7, 897-907 (2000)
[3] Chin, W.W.: The partial least squares approach to structural equation modeling. In: Marcoulides, G.A. (ed.) Modern Methods for Business Research, cap.10. Lawrence Erlbaum Associates, MahWah, New Jersey (1998)
[4] Chin W.W., Newsted, P.R.: Structural equation modeling analysis with small sampling using partial least squares. In: Hoyle, R.H. (ed.) Statistical Strategies for Small Sample Research (pp. 307-341). Sage, Newbury Park, California (1998)
[5] ECSI: European Customer Satisfaction Index: Report prepared for the ECSI Steering Committee (1998)
[6] Fornell, C.: A national customer satisfaction Barometer: the Swedish experience. J. Marketing 56, 6-21 (1992) · doi:10.2307/1252129
[7] Fornell, C., Bookstein, F.L.: The two structural equation models: LISREL and PLS applied to customer exit-voice theory. J. Marketing Res. 19, 440-452 (1982) · doi:10.2307/3151718
[8] Fornell, C., Cha, J.: Partial least squares. In: Bagozzi, R.P. (ed.) Advanced Methods of Marketing Research. Blackwell, Cambridge (1994)
[9] Fornell, C., Johnson, M.D., Anderson, E.W., Cha, J., Everitt Bryant, B.: The American customer satisfaction index: nature, purpose and findings. J. Marketing 60, 7-18 (1998) · doi:10.2307/1251898
[10] Lomöller, J. B.: Latent Variable Path Modelling with Partial Least Squares. Physica, Heidelberg (1989)
[11] Mcdonald, R.P.: Path analysis with composite variables. Multivariate Behav. Res. 31(2), 239-270 (1996) · doi:10.1207/s15327906mbr3102_5
[12] Nachtigal, C., Kroelune, K., Funke, F., Steyer, R.: (Why) should we use SEM? pros and cons of structural equation modeling. Methods Psychol. Res., Online 8(2), 1-22 (2003)
[13] Ridgon, R.E.: Structural equation modelling. In: Marcoulides, G.A. (ed.) Modern methods for business research. Lawrence Erlbaum Associates, MahWah, New Jersey (1998)
[14] Schneeweiss, H.: Models with latent variables: LISREL versus PLS. Contemp. Math. 112, 33-40 (1990) · doi:10.1090/conm/112/1087097
[15] Tenenhaus, M.: Comparisson between PLS and LISREL approaches for structural equation models. In: Vilares, Tenenhaus, Coelho Vinzi, Morinau (eds.) PLS and Related Methods-Proceedings of the PLS’03 International Conference (2003)
[16] Vilares, M.J., Almeida, M.H, Coelho, P.S.: Comparison of likelihood and PLS estimators for structural equation modelling: a simulation with customer satisfaction data. In: Vinzi, W.E., Chin, W.W., Henseler, J., Wang, H. (eds.) Handbook of Partial Least Squares. Concepts, Methods and Applications, pp. 289-307. Springer Handbooks of Computational Statistics, Springer (2010) · doi:10.1007/978-3-540-32827-8_14
[17] Vilares, M.J., Coelho, P.S.: A Satisfação e Lealdade do Cliente - Metodologias de Avaliação, Gestão e Análise, 2ł edição, Escolar Editora (2011)
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. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.