Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Next-generation prediction metrics for composite-based PLS-SEM

Next-generation prediction metrics for composite-based PLS-SEM The purpose of this study is to provide an overview of emerging prediction assessment tools for composite-based PLS-SEM, particularly proposed out-of-sample prediction methodologies.Design/methodology/approachA review of recently developed out-of-sample prediction assessment tools for composite-based PLS-SEM that will expand the skills of researchers and inform them on new methodologies for improving evaluation of theoretical models. Recently developed and proposed cross-validation approaches for model comparisons and benchmarking are reviewed and evaluated.FindingsThe results summarize next-generation prediction metrics that will substantially improve researchers' ability to assess and report the extent to which their theoretical models provide meaningful predictions. Improved prediction assessment metrics are essential to justify (practical) implications and recommendations developed on the basis of theoretical model estimation results.Originality/valueThe paper provides an overview of recently developed and proposed out-of-sample prediction metrics for composite-based PLS-SEM that will enhance the ability of researchers to demonstrate generalization of their findings from sample data to the population. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Industrial Management & Data Systems Emerald Publishing

Next-generation prediction metrics for composite-based PLS-SEM

Hair Jr, Joe F.
Industrial Management & Data Systems , Volume 121 (1): 7 – Feb 4, 2021
Download PDF
7 pages

Loading next page...
 
/lp/emerald-publishing/next-generation-prediction-metrics-for-composite-based-pls-sem-n6BKQLHdHZ
Publisher
Emerald Publishing
Copyright
© Emerald Publishing Limited
ISSN
0263-5577
DOI
10.1108/imds-08-2020-0505
Publisher site
See Article on Publisher Site

Abstract

The purpose of this study is to provide an overview of emerging prediction assessment tools for composite-based PLS-SEM, particularly proposed out-of-sample prediction methodologies.Design/methodology/approachA review of recently developed out-of-sample prediction assessment tools for composite-based PLS-SEM that will expand the skills of researchers and inform them on new methodologies for improving evaluation of theoretical models. Recently developed and proposed cross-validation approaches for model comparisons and benchmarking are reviewed and evaluated.FindingsThe results summarize next-generation prediction metrics that will substantially improve researchers' ability to assess and report the extent to which their theoretical models provide meaningful predictions. Improved prediction assessment metrics are essential to justify (practical) implications and recommendations developed on the basis of theoretical model estimation results.Originality/valueThe paper provides an overview of recently developed and proposed out-of-sample prediction metrics for composite-based PLS-SEM that will enhance the ability of researchers to demonstrate generalization of their findings from sample data to the population.

Journal

Industrial Management & Data Systems – Emerald Publishing

Published: Feb 4, 2021

Keywords: Benchmarking; Composite-based SEM; Cross-validation; Partial least squares; PLS-SEM; Out-of-sample prediction; Structural equation modeling

References

  • Foundations of the American customer satisfaction index
    Anderson, E.W.; Fornell, C.G.
  • Prediction-oriented modeling in business research by means of PLS path modeling
    Cepeda Carrión, G.; Henseler, J.; Ringle, C.M.; Roldan, J.-L.
  • Sampling weight adjustments in partial least squares structural equation modeling: guidelines and Illustrations
    Cheah, J.-H.; Roldán, J.L.; Ciavolino, E.; Ting, H.; Ramayah, T.
  • The partial least squares approach to structural equation modeling
    Chin, W.W.; Marcoulides, G.A.
  • Demystifying the role of causal-predictive modeling using partial least squares structural equation modeling in information systems research
    Chin, W.; Cheah, J.-H.; Liu, Y.; Ting, H.; Lim, X.-J.; Cham Tat, H.
  • Model selection uncertainty and multimodel inference in partial least squares structural equation modeling (PLS-SEM)
    Danks, N.P.; Sharma, P.N.; Sarstedt, M.
  • Formative vs reflective indicators in measure development: does the choice of indicators matter?
    Diamantopoulos, A.; Siguaw, J.A.
  • The American customer satisfaction index: nature, purpose, and findings
    Fornell, C.G.; Johnson, M.D.; Anderson, E.W.; Cha, J.; Bryant, B.E.
  • A predictive approach to the random effects model
    Geisser, S.
  • The nature of theory in information systems
    Gregor, S.
  • An updated and expanded assessment of PLS-SEM in information systems research
    Hair, J.F.; Hollingsworth, C.L.; Randolph, A.B.; Chong, A.
  • When to use and how to report the results of PLS-SEM
    Hair, J.F.; Risher, J.J.; Sarstedt, M.; Ringle, C.M.
  • Rethinking some of the rethinking of partial least squares
    Hair, J.F.; Sarstedt, M.; Ringle, C.M.
  • Assessing measurement model quality in PLS-SEM using confirmatory composite analysis
    Hair, J.F.; Howard, M.C.; Nitzl, .C.
  • Prediction and explanation in social systems
    Hofman, J.M.; Sharma, A.; Watts, D.J.
  • Antecedents and consequences of customer satisfaction: do they differ across online and offline purchases?
    Hult, G.T.M.; Sharma, P.N.; Morgeson, F.V.; Zhang, Y.
  • A concept analysis of methodological research on composite-based structural equation modeling: bridging PLSPM and GSCA
    Hwang, H.; Sarstedt, M.; Cheah, J.-H.; Ringle, C.M.
  • The evolution and future of national customer satisfaction index models
    Johnson, M.D.; Gustafsson, A.; Andreassen, T.W.; Lervik, L.; Cha, J.
  • The ML and PLS techniques for modeling with latent variables: historical and comparative aspects
    Jöreskog, K.G.; Wold, H.O.A.; Wold, H.O.A.; Jöreskog, K.G.
  • Structural analysis of covariance and correlation matrices
    Jöreskog, K.G.
  • Prediction: coveted, yet forsaken? Introducing a cross-validated predictive ability test in partial least squares path modeling
    Liengaard, B.; Sharma, P.N.; Hult, G.T.M.; Jensen, M.B.; Sarstedt, M.; Hair, J.F.; Ringle, C.M.
  • Predicting user intentions: comparing the technology acceptance model with the theory of planned behavior
    Mathieson, K.
  • The case of partial least squares (PLS) path modeling in managerial accounting
    Nitzl, C.; Chin, W.
  • Structural equation modeling
    Rigdon, E.E.; Marcoulides, G.A.
  • Estimation issues with PLS and CB-SEM: where the bias lies!
    Sarstedt, M.; Hair, J.F.; Ringle, C.M.; Thiele, K.O.; Gudergan, S.P.
  • Partial least squares structural equation modeling
    Sarstedt, M.; Ringle, C.M.; Hair, J.F.; Homburg, C.; Klarmann, M.; Vomberg, A.
  • Beyond a tandem analysis of SEM and PROCESS: use PLS-SEM for mediation analyses!
    Sarstedt, M.; Hair, J.F.; Nitzl, C.; Ringle, C.M.; Howard, M.C.
  • Prediction-oriented model selection in partial least squares path modeling
    Sharma, P.N.; Shmueli, G.; Sarstedt, M.; Danks, N.; Ray, S.
  • The elephant in the room: evaluating the predictive performance of PLS models
    Shmueli, G.; Ray, S.; Velasquez Estrada, J.M.; Chatla, S.B.
  • Predictive model assessment in PLS-SEM: guidelines for using PLSpredict
    Shmueli, G.; Sarstedt, M.; Hair, J.F.; Cheah, J.; Ting, H.; Vaithilingam, S.; Ringle, C.M.
  • To explain or to predict?
    Shmueli, G.
  • Cross-validatory choice and assessment of statistical predictions
    Stone, M.
  • Soft modeling: the basic design and some extensions
    Wold, H.O.A.; Jöreskog, K.G.; Wold, H.O.A.
  • Predictive analytics in information systems research
    Shmueli, G.; Koppius, O.R.