Consistent and asymptotically normal PLS estimators for linear structural equations

Theo K. Dijkstra, Jörg Henseler

Research output: Contribution to journalArticleAcademicpeer-review

170 Citations (Scopus)
65 Downloads (Pure)

Abstract

A vital extension to partial least squares (PLS) path modeling is introduced: consistency. While maintaining all the strengths of PLS, the consistent version provides two key improvements. Path coefficients, parameters of simultaneous equations, construct correlations, and indicator loadings are estimated consistently. The global goodness-of-fit of the structural model can also now be assessed, which makes PLS suitable for confirmatory research. A Monte Carlo simulation illustrates the new approach and compares it with covariance-based structural equation modeling
Original languageEnglish
Pages (from-to)10-23
JournalComputational statistics & data analysis
Volume81
Issue number1
DOIs
Publication statusPublished - 2015

Fingerprint

Structural Equations
Partial Least Squares
Least Squares Estimator
Linear equation
Path
Simultaneous equations
Structural Equation Modeling
Structural Model
Goodness of fit
Monte Carlo Simulation
Coefficient
Modeling
Monte Carlo simulation

Keywords

  • IR-91538
  • METIS-304686
  • Partial least squares (PLS)
  • Structural equation modeling (SEM)
  • Consistency
  • Recursiveness
  • Goodness-of-fit

Cite this

@article{359e0fa3d7424c76873f35a0b608041e,
title = "Consistent and asymptotically normal PLS estimators for linear structural equations",
abstract = "A vital extension to partial least squares (PLS) path modeling is introduced: consistency. While maintaining all the strengths of PLS, the consistent version provides two key improvements. Path coefficients, parameters of simultaneous equations, construct correlations, and indicator loadings are estimated consistently. The global goodness-of-fit of the structural model can also now be assessed, which makes PLS suitable for confirmatory research. A Monte Carlo simulation illustrates the new approach and compares it with covariance-based structural equation modeling",
keywords = "IR-91538, METIS-304686, Partial least squares (PLS), Structural equation modeling (SEM) , Consistency, Recursiveness, Goodness-of-fit",
author = "Dijkstra, {Theo K.} and J{\"o}rg Henseler",
note = "Open access",
year = "2015",
doi = "10.1016/j.csda.2014.07.008",
language = "English",
volume = "81",
pages = "10--23",
journal = "Computational statistics & data analysis",
issn = "0167-9473",
publisher = "Elsevier",
number = "1",

}

Consistent and asymptotically normal PLS estimators for linear structural equations. / Dijkstra, Theo K.; Henseler, Jörg.

In: Computational statistics & data analysis, Vol. 81, No. 1, 2015, p. 10-23.

Research output: Contribution to journalArticleAcademicpeer-review

TY - JOUR

T1 - Consistent and asymptotically normal PLS estimators for linear structural equations

AU - Dijkstra, Theo K.

AU - Henseler, Jörg

N1 - Open access

PY - 2015

Y1 - 2015

N2 - A vital extension to partial least squares (PLS) path modeling is introduced: consistency. While maintaining all the strengths of PLS, the consistent version provides two key improvements. Path coefficients, parameters of simultaneous equations, construct correlations, and indicator loadings are estimated consistently. The global goodness-of-fit of the structural model can also now be assessed, which makes PLS suitable for confirmatory research. A Monte Carlo simulation illustrates the new approach and compares it with covariance-based structural equation modeling

AB - A vital extension to partial least squares (PLS) path modeling is introduced: consistency. While maintaining all the strengths of PLS, the consistent version provides two key improvements. Path coefficients, parameters of simultaneous equations, construct correlations, and indicator loadings are estimated consistently. The global goodness-of-fit of the structural model can also now be assessed, which makes PLS suitable for confirmatory research. A Monte Carlo simulation illustrates the new approach and compares it with covariance-based structural equation modeling

KW - IR-91538

KW - METIS-304686

KW - Partial least squares (PLS)

KW - Structural equation modeling (SEM)

KW - Consistency

KW - Recursiveness

KW - Goodness-of-fit

U2 - 10.1016/j.csda.2014.07.008

DO - 10.1016/j.csda.2014.07.008

M3 - Article

VL - 81

SP - 10

EP - 23

JO - Computational statistics & data analysis

JF - Computational statistics & data analysis

SN - 0167-9473

IS - 1

ER -