An empirical comparison of generalized structured component analysis and partial least squares path modeling under variance-based structural equation models

  • Gyeongcheol ChoEmail author
  • Ji Yeh Choi
Original Paper


Generalized structured component analysis (GSCA) and partial least squares path modeling (PLSPM) are component-based, or also called variance-based, structural equation modeling (SEM). They define latent variables as components or weighted composites of indicators, attempting to maximize the explained variances of indicators or endogenous components or both. Despite this common conceptualization of latent variables, GSCA and PLSPM involve distinct model specifications and estimation procedures. This paper focuses on comparing four modeling approaches—GSCA with reflective indicators, GSCA with formative indicators, PLSPM with mode A, and PLSPM with mode B—regarding their capability of parameter recovery and statistical power via Monte Carlo simulation. For comparison, we propose a new data generating process for variance-based SEM, appropriate to handle all possible modeling approaches for both GSCA and PLSPM. It was found that although every approach produced consistent estimators, GSCA with reflective indicators yielded the most efficient estimators under variance-based structural equation models.


Generalized structured component analysis Partial least squares path modeling Data generating process for variance-based structural equation models Comparison Simulation 


Compliance with ethical standards

Conflict of interest

On behalf of all authors, the corresponding author states that there is no conflict of interest.

Supplementary material

41237_2019_98_MOESM1_ESM.docx (58 kb)
Supplementary material 1 (DOCX 59 kb)


  1. Anderson EW, Fornell C (2002) Foundations of the American customer satisfaction index. Total Qual Manag 11(7):869–882. CrossRefGoogle Scholar
  2. Becker J-M, Rai A, Rigdon E (2013) Predictive validity and formative measurement in structural equation modeling: embracing practical relevance. In: Proceedings of the 34th international conference on information systems (ICIS), Milan, ItalyGoogle Scholar
  3. Bollen KA (1989) Structural equations with latent variables. Wiley, Hoboken. CrossRefzbMATHGoogle Scholar
  4. Bollen KA (1996) An alternative two stage least squares (2SLS) estimator for latent variable equations. Psychometrika 61(1):109–121. MathSciNetCrossRefzbMATHGoogle Scholar
  5. Bollen KA (2011) Evaluating effect, composite, and causal indicators in structural equation models. MIS Q 35(2):359. CrossRefGoogle Scholar
  6. Bollen KA, Kirby JB, Curran PJ, Paxton PM, Chen F (2007) Latent variable models under misspecification two-stage least squares (2SLS) and maximum likelihood (ML) estimators. Soc Methods Res 36(1):48–86. MathSciNetCrossRefGoogle Scholar
  7. Chai T, Draxler RR (2014) Root mean square error (RMSE) or mean absolute error (MAE)? Arguments against avoiding RMSE in the literature. Geosci Model Dev 7(3):1247–1250. CrossRefGoogle Scholar
  8. Chin WW (1998) The partial least squares approach for structural equation modeling. In: Marcoulides GA (ed) Methodology for business and management. Modern methods for business research. Lawrence Erlbaum Associates Publishers, Mahwah, NJ, US, pp 295–336Google Scholar
  9. Cho G, Jung K, Hwang H (2019) Out-of-bag prediction error: a cross validation index for generalized structured component analysis. Multivar Behav Res. CrossRefGoogle Scholar
  10. Cronbach LJ, Meehl PE (1955) Construct validity in psychological tests. Psychol Bull 52(4):281–302CrossRefGoogle Scholar
  11. Dijkstra TK (2017) A perfect match between a model and a mode. In: Partial least squares path modeling: basic concepts, methodological issues and applications. Springer, Berlin, pp 55–80. CrossRefGoogle Scholar
  12. Efron B (1979) Bootstrap methods: another look at the jackknife. Ann Stat 7(1):1–26. MathSciNetCrossRefzbMATHGoogle Scholar
  13. Eklöf JA, Westlund AH (2002) The pan-European customer satisfaction index programme—current work and the way ahead. Total Qual Manag 13(8):1099–1106. CrossRefGoogle Scholar
  14. Fomby TB, Johnson SR, Hill RC (2011) Advanced econometric methods. Advanced econometric methods. Springer, New York. CrossRefzbMATHGoogle Scholar
  15. Fornell C, Johnson MD, Anderson EW, Cha J, Bryant BE (1996) The American customer satisfaction index: nature, purpose, and findings. J Mark 60(4):7. CrossRefGoogle Scholar
  16. Gallier J, Quaintance J (2019) Algebra, topology, differential calculus, and optimization theory for computer science and engineering. Philadelphia, PA. Retrieved Feb 20, 2019, from
  17. Gerbing DW, Hamilton JG (1994) The surprising viability of a simple alternate estimation procedure for construction of large-scale structural equation measurement models. Struct Equ Model A Multidiscip J 1(2):103–115. CrossRefGoogle Scholar
  18. Hair JF, Hult GTM, Ringle CM, Sarstedt M, Thiele KO (2017) Mirror, mirror on the wall: a comparative evaluation of composite-based structural equation modeling methods. J Acad Mark Sci 45(5):616–632. CrossRefGoogle Scholar
  19. Hwang H, Takane Y (2014) Generalized structured component analysis: a component-based approach to structural equation modeling. Chapman and Hall/CRC Press, New YorkCrossRefGoogle Scholar
  20. Hwang H, Malhotra NK, Kim Y, Tomiuk MA, Hong S (2010) A comparative study on parameter recovery of three approaches to structural equation modeling. J Mark Res 47(4):699–712. CrossRefGoogle Scholar
  21. Hwang H, Takane Y, Tenenhaus A (2015) An alternative estimation procedure for partial least squares path modeling. Behaviormetrika 42(1):63–78. CrossRefGoogle Scholar
  22. Hwang H, Sarstedt M, Cheah JH, Ringle CM (2019) A concept analysis of methodological research on composite-based structural equation modeling: bridging PLSPM and GSCA. Behaviormetrika. CrossRefGoogle Scholar
  23. Jarvis CB, MacKenzie SB, Podsakoff PM (2003) A critical review of construct indicators and measurement model misspecification in marketing and consumer research. J Consum Res 30(2):199–218. CrossRefGoogle Scholar
  24. Jöreskog KG (1970) Estimation and testing of simplex models. Br J Math Stat Psychol 23(2):121–145. CrossRefzbMATHGoogle Scholar
  25. Jöreskog KG (1978) Structural analysis of covariance and correlation matrices. Psychometrika 43(4):443–477. MathSciNetCrossRefzbMATHGoogle Scholar
  26. Lay DC, Lay SR, McDonald JJ (2015) Linear algebra and its applications, 576Google Scholar
  27. Lohmöller J-B (1989) Latent variable path modeling with partial least squares. Springer, New York. CrossRefzbMATHGoogle Scholar
  28. Marsh HW, Hau KT, Balla JR, Grayson D (1998) Is more ever too much? The number of indicators per factor in confirmatory factor analysis. Multivar Behav Res 33(2):181–220. CrossRefGoogle Scholar
  29. Rego LL, Morgan NA, Fornell C (2013) Reexamining the market share-customer satisfaction relationship. J Mark 77(5):1–20. CrossRefGoogle Scholar
  30. Reinartz W, Haenlein M, Henseler J (2009) An empirical comparison of the efficacy of covariance-based and variance-based SEM. Int J Res Mark 26(4):332–344. CrossRefGoogle Scholar
  31. Rigdon EE (2012) Rethinking partial least squares path modeling: in praise of simple methods. Long Range Plan 45(5–6):341–358. CrossRefGoogle Scholar
  32. Roldán JL, Sánchez-Franco MJ (2012) Variance-based structural equation modeling: guidelines for using partial least squares in information systems research. In: Mora M, Gelman O, Steenkamp AL, Raisinghani M (eds) Research methodologies, innovations and philosophies in software systems engineering and information systems. IGI Global, Hershey, pp 193–221. CrossRefGoogle Scholar
  33. Sarstedt M, Hair JF, Ringle CM, Thiele KO, Gudergan SP (2016) Estimation issues with PLS and CBSEM: where the bias lies! J Bus Res 69(10):3998–4010. CrossRefGoogle Scholar
  34. Sharma PN, Shmueli G, Sarstedt M, Danks N, Ray S (2018) Prediction-oriented model selection in partial least squares path modeling. Decis Sci 00:1–41. CrossRefGoogle Scholar
  35. Shmueli G, Ray S, Velasquez Estrada JM, Chatla SB (2016) The elephant in the room: predictive performance of PLS models. J Bus Res 69(10):4552–4564. CrossRefGoogle Scholar
  36. Tenenhaus M (2008) Component-based structural equation modelling. Total Quality Manag Bus Excell 19(7–8):871–886. CrossRefGoogle Scholar
  37. Tenenhaus M, Esposito Vinzi V, Chatelin Y-M, Lauro C (2005) PLS path modeling. Comput Stat Data Anal 48(1):159–205. MathSciNetCrossRefzbMATHGoogle Scholar
  38. Wold H (1982) Models for knowledge. In: Gani J (ed) The making of statisticians. Springer, New York, pp 189–212. CrossRefGoogle Scholar

Copyright information

© The Behaviormetric Society 2019

Authors and Affiliations

  1. 1.Department of PsychologyMcGill UniversityMontrealCanada
  2. 2.Department of PsychologyYork UniversityTorontoCanada

Personalised recommendations