Assessing and testing the goodness-of-fit of PLS path models

Research output: Contribution to conferencePaperAcademicpeer-review

Abstract

This paper introduces a family of goodness-of-fit measures for partial least squares path modeling (PLS). It shows that PLS estimates the parameters of a composite factor model. The discrepancy between the empirical covariance matrix and the covariance matrix implied by the composite factor model permits quantifying the model fit. The paper proposes statistical inference based on the bootstrap as an exact test of model fit. Moreover, it suggests the standardized root mean square residual as an approximate measure of model fit. These two goodness-of-fit measures enable analysts to empirically assess the validity of interrelated composites of observed variables, i.e., conduct a confirmatory composite analysis by means of PLS. Finally, the paper provides recommendations for conducting and reporting typical PLS analyses.
Original languageEnglish
Publication statusPublished - 9 May 2014
EventThe 3rd Annual Conference of the Dutch/Flemish Classification Society (Vereniging voor Ordinatie en Classificatie - VOC) - Leiden, Netherlands
Duration: 9 May 20149 May 2014
Conference number: 3

Conference

ConferenceThe 3rd Annual Conference of the Dutch/Flemish Classification Society (Vereniging voor Ordinatie en Classificatie - VOC)
Abbreviated title3rd VOC Conference
CountryNetherlands
CityLeiden
Period9/05/149/05/14

Fingerprint

Testing
Goodness of fit
Path model
Covariance matrix
Bootstrap
Exact test
Analysts
Statistical inference
Partial least squares
Discrepancy
Modeling

Cite this

Henseler, J. (2014). Assessing and testing the goodness-of-fit of PLS path models. Paper presented at The 3rd Annual Conference of the Dutch/Flemish Classification Society (Vereniging voor Ordinatie en Classificatie - VOC), Leiden, Netherlands.
Henseler, Jörg . / Assessing and testing the goodness-of-fit of PLS path models. Paper presented at The 3rd Annual Conference of the Dutch/Flemish Classification Society (Vereniging voor Ordinatie en Classificatie - VOC), Leiden, Netherlands.
@conference{69d7cb0e6fe74a44a71fa64528065cb4,
title = "Assessing and testing the goodness-of-fit of PLS path models",
abstract = "This paper introduces a family of goodness-of-fit measures for partial least squares path modeling (PLS). It shows that PLS estimates the parameters of a composite factor model. The discrepancy between the empirical covariance matrix and the covariance matrix implied by the composite factor model permits quantifying the model fit. The paper proposes statistical inference based on the bootstrap as an exact test of model fit. Moreover, it suggests the standardized root mean square residual as an approximate measure of model fit. These two goodness-of-fit measures enable analysts to empirically assess the validity of interrelated composites of observed variables, i.e., conduct a confirmatory composite analysis by means of PLS. Finally, the paper provides recommendations for conducting and reporting typical PLS analyses.",
author = "J{\"o}rg Henseler",
year = "2014",
month = "5",
day = "9",
language = "English",
note = "The 3rd Annual Conference of the Dutch/Flemish Classification Society (Vereniging voor Ordinatie en Classificatie - VOC), 3rd VOC Conference ; Conference date: 09-05-2014 Through 09-05-2014",

}

Henseler, J 2014, 'Assessing and testing the goodness-of-fit of PLS path models' Paper presented at The 3rd Annual Conference of the Dutch/Flemish Classification Society (Vereniging voor Ordinatie en Classificatie - VOC), Leiden, Netherlands, 9/05/14 - 9/05/14, .

Assessing and testing the goodness-of-fit of PLS path models. / Henseler, Jörg .

2014. Paper presented at The 3rd Annual Conference of the Dutch/Flemish Classification Society (Vereniging voor Ordinatie en Classificatie - VOC), Leiden, Netherlands.

Research output: Contribution to conferencePaperAcademicpeer-review

TY - CONF

T1 - Assessing and testing the goodness-of-fit of PLS path models

AU - Henseler, Jörg

PY - 2014/5/9

Y1 - 2014/5/9

N2 - This paper introduces a family of goodness-of-fit measures for partial least squares path modeling (PLS). It shows that PLS estimates the parameters of a composite factor model. The discrepancy between the empirical covariance matrix and the covariance matrix implied by the composite factor model permits quantifying the model fit. The paper proposes statistical inference based on the bootstrap as an exact test of model fit. Moreover, it suggests the standardized root mean square residual as an approximate measure of model fit. These two goodness-of-fit measures enable analysts to empirically assess the validity of interrelated composites of observed variables, i.e., conduct a confirmatory composite analysis by means of PLS. Finally, the paper provides recommendations for conducting and reporting typical PLS analyses.

AB - This paper introduces a family of goodness-of-fit measures for partial least squares path modeling (PLS). It shows that PLS estimates the parameters of a composite factor model. The discrepancy between the empirical covariance matrix and the covariance matrix implied by the composite factor model permits quantifying the model fit. The paper proposes statistical inference based on the bootstrap as an exact test of model fit. Moreover, it suggests the standardized root mean square residual as an approximate measure of model fit. These two goodness-of-fit measures enable analysts to empirically assess the validity of interrelated composites of observed variables, i.e., conduct a confirmatory composite analysis by means of PLS. Finally, the paper provides recommendations for conducting and reporting typical PLS analyses.

M3 - Paper

ER -

Henseler J. Assessing and testing the goodness-of-fit of PLS path models. 2014. Paper presented at The 3rd Annual Conference of the Dutch/Flemish Classification Society (Vereniging voor Ordinatie en Classificatie - VOC), Leiden, Netherlands.