Residual analysis for unidimensional scaling in the L2-norm

Michael J. Brusco, Douglas Steinley, Hans Friedrich Koehn

Research output: Contribution to journalArticle

Abstract

We present a procedure (RAUS) for residual analysis of a dissimilarity matrix whereby unidimensional scaling is successively applied to the absolute value of residuals. A key advantage of RAUS is that the efficient Defays formulation of unidimensional scaling can be used for the fitting of each scale. An example using U.S. Supreme Court voting data is provided to illustrate the interpretation of successive scales. A simulation study was performed to evaluate RAUS.

Original languageEnglish (US)
Pages (from-to)2210-2221
Number of pages12
JournalCommunications in Statistics: Simulation and Computation
Volume48
Issue number7
DOIs
StatePublished - Aug 9 2019

Fingerprint

Residual Analysis
Scaling
Norm
Dissimilarity
Voting
Absolute value
Simulation Study
Formulation
Evaluate
Interpretation

Keywords

  • Combinatorial data analysis
  • Least-squares unidimensional scaling: Residual analysis
  • Simulated annealing

ASJC Scopus subject areas

  • Statistics and Probability
  • Modeling and Simulation

Cite this

Residual analysis for unidimensional scaling in the L2-norm. / Brusco, Michael J.; Steinley, Douglas; Koehn, Hans Friedrich.

In: Communications in Statistics: Simulation and Computation, Vol. 48, No. 7, 09.08.2019, p. 2210-2221.

Research output: Contribution to journalArticle

@article{99abddee05c146459eb34e782701bb56,
title = "Residual analysis for unidimensional scaling in the L2-norm",
abstract = "We present a procedure (RAUS) for residual analysis of a dissimilarity matrix whereby unidimensional scaling is successively applied to the absolute value of residuals. A key advantage of RAUS is that the efficient Defays formulation of unidimensional scaling can be used for the fitting of each scale. An example using U.S. Supreme Court voting data is provided to illustrate the interpretation of successive scales. A simulation study was performed to evaluate RAUS.",
keywords = "Combinatorial data analysis, Least-squares unidimensional scaling: Residual analysis, Simulated annealing",
author = "Brusco, {Michael J.} and Douglas Steinley and Koehn, {Hans Friedrich}",
year = "2019",
month = "8",
day = "9",
doi = "10.1080/03610918.2018.1438620",
language = "English (US)",
volume = "48",
pages = "2210--2221",
journal = "Communications in Statistics Part B: Simulation and Computation",
issn = "0361-0918",
publisher = "Taylor and Francis Ltd.",
number = "7",

}

TY - JOUR

T1 - Residual analysis for unidimensional scaling in the L2-norm

AU - Brusco, Michael J.

AU - Steinley, Douglas

AU - Koehn, Hans Friedrich

PY - 2019/8/9

Y1 - 2019/8/9

N2 - We present a procedure (RAUS) for residual analysis of a dissimilarity matrix whereby unidimensional scaling is successively applied to the absolute value of residuals. A key advantage of RAUS is that the efficient Defays formulation of unidimensional scaling can be used for the fitting of each scale. An example using U.S. Supreme Court voting data is provided to illustrate the interpretation of successive scales. A simulation study was performed to evaluate RAUS.

AB - We present a procedure (RAUS) for residual analysis of a dissimilarity matrix whereby unidimensional scaling is successively applied to the absolute value of residuals. A key advantage of RAUS is that the efficient Defays formulation of unidimensional scaling can be used for the fitting of each scale. An example using U.S. Supreme Court voting data is provided to illustrate the interpretation of successive scales. A simulation study was performed to evaluate RAUS.

KW - Combinatorial data analysis

KW - Least-squares unidimensional scaling: Residual analysis

KW - Simulated annealing

UR - http://www.scopus.com/inward/record.url?scp=85042911562&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85042911562&partnerID=8YFLogxK

U2 - 10.1080/03610918.2018.1438620

DO - 10.1080/03610918.2018.1438620

M3 - Article

AN - SCOPUS:85042911562

VL - 48

SP - 2210

EP - 2221

JO - Communications in Statistics Part B: Simulation and Computation

JF - Communications in Statistics Part B: Simulation and Computation

SN - 0361-0918

IS - 7

ER -