Model based methods for performing multi-way non-symmetric correspondence analysis

Eric J. Beh; Rosaria Lombardo; Biagio Simonetti; Enrico Ciavolino

Model based methods for performing multi-way non-symmetric correspondence analysis

Eric J. Beh, Rosaria Lombardo, Biagio Simonetti, Enrico Ciavolino

Research output: Chapter in Book / Conference Paper › Conference Paper

Abstract

![CDATA[Traditionally multiple correspondence analysis involves transforming a contingency table to its indicator or Burt matrix form then performing the classical two-way approach. Alternatively, one may also consider techniques that are more model based such as the partitions associated with the PARAFAC/CANDECOMP models or the Tucker3 model. Traditionally these procedures have proven to be of benefit in studies where the variables are nominally structured. This paper will demonstrate how they can be adapted for ordinal variables by incorporating orthogonal polynomials into the partitions and a graphical description of the association can be obtained by considering correspondence analysis. This paper will also consider the case where the variables of a three-way contingency table are asymmetrically associated.]]

Original language	English
Title of host publication	MTISD 2008: Methods, Models and Information Technologies for Decision Support Systems: Proceedings of conference held at University of Salento, Lecce, Italy, 18-20 September, 2008
Publisher	University of Salento
Number of pages	4
ISBN (Print)	9788883050619
Publication status	Published - 2008
Event	Conference on Methods, Models and Information Technologies for Decision Support Systems - Duration: 1 Jan 2008 → …

Conference

Conference	Conference on Methods, Models and Information Technologies for Decision Support Systems
Period	1/01/08 → …

Keywords

contingency tables
orthogonal polynomials
correspondence analysis (statistics)

Cite this

@inproceedings{ac2e62db6b70468a8542625806e0ae90,

title = "Model based methods for performing multi-way non-symmetric correspondence analysis",

abstract = "![CDATA[Traditionally multiple correspondence analysis involves transforming a contingency table to its indicator or Burt matrix form then performing the classical two-way approach. Alternatively, one may also consider techniques that are more model based such as the partitions associated with the PARAFAC/CANDECOMP models or the Tucker3 model. Traditionally these procedures have proven to be of benefit in studies where the variables are nominally structured. This paper will demonstrate how they can be adapted for ordinal variables by incorporating orthogonal polynomials into the partitions and a graphical description of the association can be obtained by considering correspondence analysis. This paper will also consider the case where the variables of a three-way contingency table are asymmetrically associated.]]",

keywords = "contingency tables, orthogonal polynomials, correspondence analysis (statistics)",

author = "Beh, {Eric J.} and Rosaria Lombardo and Biagio Simonetti and Enrico Ciavolino",

year = "2008",

language = "English",

isbn = "9788883050619",

booktitle = "MTISD 2008: Methods, Models and Information Technologies for Decision Support Systems: Proceedings of conference held at University of Salento, Lecce, Italy, 18-20 September, 2008",

publisher = "University of Salento",

note = "Conference on Methods, Models and Information Technologies for Decision Support Systems ; Conference date: 01-01-2008",

}

Beh, EJ, Lombardo, R, Simonetti, B & Ciavolino, E 2008, Model based methods for performing multi-way non-symmetric correspondence analysis. in MTISD 2008: Methods, Models and Information Technologies for Decision Support Systems: Proceedings of conference held at University of Salento, Lecce, Italy, 18-20 September, 2008. University of Salento, Conference on Methods, Models and Information Technologies for Decision Support Systems, 1/01/08.

Model based methods for performing multi-way non-symmetric correspondence analysis. / Beh, Eric J.; Lombardo, Rosaria; Simonetti, Biagio et al.
MTISD 2008: Methods, Models and Information Technologies for Decision Support Systems: Proceedings of conference held at University of Salento, Lecce, Italy, 18-20 September, 2008. University of Salento, 2008.

Research output: Chapter in Book / Conference Paper › Conference Paper

TY - GEN

T1 - Model based methods for performing multi-way non-symmetric correspondence analysis

AU - Beh, Eric J.

AU - Lombardo, Rosaria

AU - Simonetti, Biagio

AU - Ciavolino, Enrico

PY - 2008

Y1 - 2008

N2 - ![CDATA[Traditionally multiple correspondence analysis involves transforming a contingency table to its indicator or Burt matrix form then performing the classical two-way approach. Alternatively, one may also consider techniques that are more model based such as the partitions associated with the PARAFAC/CANDECOMP models or the Tucker3 model. Traditionally these procedures have proven to be of benefit in studies where the variables are nominally structured. This paper will demonstrate how they can be adapted for ordinal variables by incorporating orthogonal polynomials into the partitions and a graphical description of the association can be obtained by considering correspondence analysis. This paper will also consider the case where the variables of a three-way contingency table are asymmetrically associated.]]

AB - ![CDATA[Traditionally multiple correspondence analysis involves transforming a contingency table to its indicator or Burt matrix form then performing the classical two-way approach. Alternatively, one may also consider techniques that are more model based such as the partitions associated with the PARAFAC/CANDECOMP models or the Tucker3 model. Traditionally these procedures have proven to be of benefit in studies where the variables are nominally structured. This paper will demonstrate how they can be adapted for ordinal variables by incorporating orthogonal polynomials into the partitions and a graphical description of the association can be obtained by considering correspondence analysis. This paper will also consider the case where the variables of a three-way contingency table are asymmetrically associated.]]

KW - contingency tables

KW - orthogonal polynomials

KW - correspondence analysis (statistics)

UR - http://handle.uws.edu.au:8081/1959.7/45190

M3 - Conference Paper

SN - 9788883050619

BT - MTISD 2008: Methods, Models and Information Technologies for Decision Support Systems: Proceedings of conference held at University of Salento, Lecce, Italy, 18-20 September, 2008

PB - University of Salento

T2 - Conference on Methods, Models and Information Technologies for Decision Support Systems

Y2 - 1 January 2008

ER -

Model based methods for performing multi-way non-symmetric correspondence analysis

Abstract

Conference

Keywords

Other files and links

Fingerprint

Cite this