Response-based segmentation using Finite Mixture Partial Least Squares: theoretical foundations and an application to American Customer Satisfaction Index Data

Christian M. Ringle, Marko Sarstedt, Erik A. Mooi

Research output: Chapter in Book/Report/Conference proceedingChapter

Abstract

When applying multivariate analysis techniques in information systems and social science disciplines, such as management information systems (MIS) and marketing, the assumption that the empirical data originate from a single homogeneous population is often unrealistic. When applying a causal modeling approach, such as partial least squares (PLS) path modeling, segmentation is a key issue in coping with the problem of heterogeneity in estimated cause-and-effect relationships. This chapter presents a new PLS path modeling approach which classifies units on the basis of the heterogeneity of the estimates in the inner model. If unobserved heterogeneity significantly affects the estimated path model relationships on the aggregate data level, the methodology will allow homogenous groups of observations to be created that exhibit distinctive path model estimates. The approach will, thus, provide differentiated analytical outcomes that permit more precise interpretations of each segment formed. An application on a large data set in an example of the American customer satisfaction index (ACSI) substantiates the methodology’s effectiveness in evaluating PLS path modeling results.
Original languageEnglish
Title of host publicationData mining: special issue in annals of information systems
EditorsRobert Stahlbock, Sven F. Crone, Stefan Lessmann
Place of PublicationLondon (UK)
PublisherSpringer
Pages19-49
Number of pages31
Volume8
ISBN (Print)978-1-44191279-4
DOIs
Publication statusPublished - 2010

Publication series

NameAnnals of Information Systems
PublisherSpringer

Fingerprint

Partial least squares
Segmentation
Customer satisfaction
Finite mixture
Modeling
Path model
Systems science
Information systems
Causal modeling
Methodology
Management information systems
Empirical data
Unobserved heterogeneity
Social sciences
Aggregate data
Marketing
Multivariate analysis

Keywords

  • multivariate analysis techniques
  • information systems
  • social science disciplines
  • management information systems
  • MIS
  • marketing
  • empirical data
  • causal modeling approach
  • partial least squares
  • PLS
  • path modeling
  • segmentation
  • heterogeneity

Cite this

Ringle, C. M., Sarstedt, M., & Mooi, E. A. (2010). Response-based segmentation using Finite Mixture Partial Least Squares: theoretical foundations and an application to American Customer Satisfaction Index Data. In R. Stahlbock, S. F. Crone, & S. Lessmann (Eds.), Data mining: special issue in annals of information systems (Vol. 8, pp. 19-49). (Annals of Information Systems). London (UK): Springer. https://doi.org/10.1007/978-1-4419-1280-0_2
Ringle, Christian M. ; Sarstedt, Marko ; Mooi, Erik A. / Response-based segmentation using Finite Mixture Partial Least Squares: theoretical foundations and an application to American Customer Satisfaction Index Data. Data mining: special issue in annals of information systems. editor / Robert Stahlbock ; Sven F. Crone ; Stefan Lessmann. Vol. 8 London (UK) : Springer, 2010. pp. 19-49 (Annals of Information Systems).
@inbook{9fa58e9ebc8b4a01a7a9c6a38b084861,
title = "Response-based segmentation using Finite Mixture Partial Least Squares: theoretical foundations and an application to American Customer Satisfaction Index Data",
abstract = "When applying multivariate analysis techniques in information systems and social science disciplines, such as management information systems (MIS) and marketing, the assumption that the empirical data originate from a single homogeneous population is often unrealistic. When applying a causal modeling approach, such as partial least squares (PLS) path modeling, segmentation is a key issue in coping with the problem of heterogeneity in estimated cause-and-effect relationships. This chapter presents a new PLS path modeling approach which classifies units on the basis of the heterogeneity of the estimates in the inner model. If unobserved heterogeneity significantly affects the estimated path model relationships on the aggregate data level, the methodology will allow homogenous groups of observations to be created that exhibit distinctive path model estimates. The approach will, thus, provide differentiated analytical outcomes that permit more precise interpretations of each segment formed. An application on a large data set in an example of the American customer satisfaction index (ACSI) substantiates the methodology’s effectiveness in evaluating PLS path modeling results.",
keywords = "multivariate analysis techniques, information systems, social science disciplines, management information systems, MIS, marketing, empirical data, causal modeling approach, partial least squares, PLS, path modeling, segmentation, heterogeneity",
author = "Ringle, {Christian M.} and Marko Sarstedt and Mooi, {Erik A.}",
year = "2010",
doi = "10.1007/978-1-4419-1280-0_2",
language = "English",
isbn = "978-1-44191279-4",
volume = "8",
series = "Annals of Information Systems",
publisher = "Springer",
pages = "19--49",
editor = "Robert Stahlbock and Crone, {Sven F.} and Stefan Lessmann",
booktitle = "Data mining: special issue in annals of information systems",
address = "Germany",

}

Ringle, CM, Sarstedt, M & Mooi, EA 2010, Response-based segmentation using Finite Mixture Partial Least Squares: theoretical foundations and an application to American Customer Satisfaction Index Data. in R Stahlbock, SF Crone & S Lessmann (eds), Data mining: special issue in annals of information systems. vol. 8, Annals of Information Systems, Springer, London (UK), pp. 19-49. https://doi.org/10.1007/978-1-4419-1280-0_2

Response-based segmentation using Finite Mixture Partial Least Squares: theoretical foundations and an application to American Customer Satisfaction Index Data. / Ringle, Christian M.; Sarstedt, Marko; Mooi, Erik A.

Data mining: special issue in annals of information systems. ed. / Robert Stahlbock; Sven F. Crone; Stefan Lessmann. Vol. 8 London (UK) : Springer, 2010. p. 19-49 (Annals of Information Systems).

Research output: Chapter in Book/Report/Conference proceedingChapter

TY - CHAP

T1 - Response-based segmentation using Finite Mixture Partial Least Squares: theoretical foundations and an application to American Customer Satisfaction Index Data

AU - Ringle, Christian M.

AU - Sarstedt, Marko

AU - Mooi, Erik A.

PY - 2010

Y1 - 2010

N2 - When applying multivariate analysis techniques in information systems and social science disciplines, such as management information systems (MIS) and marketing, the assumption that the empirical data originate from a single homogeneous population is often unrealistic. When applying a causal modeling approach, such as partial least squares (PLS) path modeling, segmentation is a key issue in coping with the problem of heterogeneity in estimated cause-and-effect relationships. This chapter presents a new PLS path modeling approach which classifies units on the basis of the heterogeneity of the estimates in the inner model. If unobserved heterogeneity significantly affects the estimated path model relationships on the aggregate data level, the methodology will allow homogenous groups of observations to be created that exhibit distinctive path model estimates. The approach will, thus, provide differentiated analytical outcomes that permit more precise interpretations of each segment formed. An application on a large data set in an example of the American customer satisfaction index (ACSI) substantiates the methodology’s effectiveness in evaluating PLS path modeling results.

AB - When applying multivariate analysis techniques in information systems and social science disciplines, such as management information systems (MIS) and marketing, the assumption that the empirical data originate from a single homogeneous population is often unrealistic. When applying a causal modeling approach, such as partial least squares (PLS) path modeling, segmentation is a key issue in coping with the problem of heterogeneity in estimated cause-and-effect relationships. This chapter presents a new PLS path modeling approach which classifies units on the basis of the heterogeneity of the estimates in the inner model. If unobserved heterogeneity significantly affects the estimated path model relationships on the aggregate data level, the methodology will allow homogenous groups of observations to be created that exhibit distinctive path model estimates. The approach will, thus, provide differentiated analytical outcomes that permit more precise interpretations of each segment formed. An application on a large data set in an example of the American customer satisfaction index (ACSI) substantiates the methodology’s effectiveness in evaluating PLS path modeling results.

KW - multivariate analysis techniques

KW - information systems

KW - social science disciplines

KW - management information systems

KW - MIS

KW - marketing

KW - empirical data

KW - causal modeling approach

KW - partial least squares

KW - PLS

KW - path modeling

KW - segmentation

KW - heterogeneity

UR - http://www.springerlink.com/content/j4543621w61w375m/

U2 - 10.1007/978-1-4419-1280-0_2

DO - 10.1007/978-1-4419-1280-0_2

M3 - Chapter

SN - 978-1-44191279-4

VL - 8

T3 - Annals of Information Systems

SP - 19

EP - 49

BT - Data mining: special issue in annals of information systems

A2 - Stahlbock, Robert

A2 - Crone, Sven F.

A2 - Lessmann, Stefan

PB - Springer

CY - London (UK)

ER -

Ringle CM, Sarstedt M, Mooi EA. Response-based segmentation using Finite Mixture Partial Least Squares: theoretical foundations and an application to American Customer Satisfaction Index Data. In Stahlbock R, Crone SF, Lessmann S, editors, Data mining: special issue in annals of information systems. Vol. 8. London (UK): Springer. 2010. p. 19-49. (Annals of Information Systems). https://doi.org/10.1007/978-1-4419-1280-0_2