A comparison study and discussion of the Mahalanobis-Taguchi System

Seoung Bum Kim; Kwok Leung Tsui; Thuntee Sukchotrat; Victoria C.P. Chen

doi:10.1504/IJISE.2009.026768

A comparison study and discussion of the Mahalanobis-Taguchi System

Seoung Bum Kim, Kwok Leung Tsui, Thuntee Sukchotrat, Victoria C.P. Chen

Research output: Contribution to journal › Article › peer-review

26 Citations (Scopus)

Abstract

The Mahalanobis-Taguchi System (MTS) is a diagnostic tool for selecting the appropriate variables and quantifying the degree of abnormality in the group that needs to be diagnosed. MTS is said to be 'data analytic' rather than 'probability distribution based'. This statement has brought out some controversy in the statistics community. Despite the simplicity of MTS, it is considered ad hoc owing to the lack of statistical and probability theory. In this paper, we attempt to incorporate statistical thinking into the ad hoc parts of MTS by comparing with other multivariate statistical methods.

Original language	English
Pages (from-to)	631-644
Number of pages	14
Journal	International Journal of Industrial and Systems Engineering
Volume	4
Issue number	6
DOIs	https://doi.org/10.1504/IJISE.2009.026768
Publication status	Published - 2009
Externally published	Yes

Keywords

Hotelling's T2
Loss functions
MTS
Mahalanobis-Taguchi system
PCA
Principal component analysis
Tree-based methods

ASJC Scopus subject areas

Control and Systems Engineering
Industrial and Manufacturing Engineering

Access to Document

10.1504/IJISE.2009.026768

Cite this

@article{5cc118ad070746248c1e969db61b12d5,

title = "A comparison study and discussion of the Mahalanobis-Taguchi System",

abstract = "The Mahalanobis-Taguchi System (MTS) is a diagnostic tool for selecting the appropriate variables and quantifying the degree of abnormality in the group that needs to be diagnosed. MTS is said to be 'data analytic' rather than 'probability distribution based'. This statement has brought out some controversy in the statistics community. Despite the simplicity of MTS, it is considered ad hoc owing to the lack of statistical and probability theory. In this paper, we attempt to incorporate statistical thinking into the ad hoc parts of MTS by comparing with other multivariate statistical methods.",

keywords = "Hotelling's T2, Loss functions, MTS, Mahalanobis-Taguchi system, PCA, Principal component analysis, Tree-based methods",

author = "{Bum Kim}, Seoung and Tsui, {Kwok Leung} and Thuntee Sukchotrat and Chen, {Victoria C.P.}",

year = "2009",

doi = "10.1504/IJISE.2009.026768",

language = "English",

volume = "4",

pages = "631--644",

journal = "International Journal of Industrial and Systems Engineering",

issn = "1748-5037",

publisher = "Inderscience Enterprises Ltd",

number = "6",

}

TY - JOUR

T1 - A comparison study and discussion of the Mahalanobis-Taguchi System

AU - Bum Kim, Seoung

AU - Tsui, Kwok Leung

AU - Sukchotrat, Thuntee

AU - Chen, Victoria C.P.

PY - 2009

Y1 - 2009

N2 - The Mahalanobis-Taguchi System (MTS) is a diagnostic tool for selecting the appropriate variables and quantifying the degree of abnormality in the group that needs to be diagnosed. MTS is said to be 'data analytic' rather than 'probability distribution based'. This statement has brought out some controversy in the statistics community. Despite the simplicity of MTS, it is considered ad hoc owing to the lack of statistical and probability theory. In this paper, we attempt to incorporate statistical thinking into the ad hoc parts of MTS by comparing with other multivariate statistical methods.

AB - The Mahalanobis-Taguchi System (MTS) is a diagnostic tool for selecting the appropriate variables and quantifying the degree of abnormality in the group that needs to be diagnosed. MTS is said to be 'data analytic' rather than 'probability distribution based'. This statement has brought out some controversy in the statistics community. Despite the simplicity of MTS, it is considered ad hoc owing to the lack of statistical and probability theory. In this paper, we attempt to incorporate statistical thinking into the ad hoc parts of MTS by comparing with other multivariate statistical methods.

KW - Hotelling's T2

KW - Loss functions

KW - MTS

KW - Mahalanobis-Taguchi system

KW - PCA

KW - Principal component analysis

KW - Tree-based methods

UR - http://www.scopus.com/inward/record.url?scp=67650115478&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=67650115478&partnerID=8YFLogxK

U2 - 10.1504/IJISE.2009.026768

DO - 10.1504/IJISE.2009.026768

M3 - Article

AN - SCOPUS:67650115478

SN - 1748-5037

VL - 4

SP - 631

EP - 644

JO - International Journal of Industrial and Systems Engineering

JF - International Journal of Industrial and Systems Engineering

IS - 6

ER -

A comparison study and discussion of the Mahalanobis-Taguchi System

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this