A parametric procedure for ultrametric tree estimation from conditional rank order proximity data

Martin R. Young, Wayne Desarbo

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

The psychometric and classification literatures have illustrated the fact that a wide class of discrete or network models (e.g., hierarchical or ultrametric trees) for the analysis of ordinal proximity data are plagued by potential degenerate solutions if estimated using traditional nonmetric procedures (i.e., procedures which optimize a STRESS-based criteria of fit and whose solutions are invariant under a monotone transformation of the input data). This paper proposes a new parametric, maximum likelihood based procedure for estimating ultrametric trees for the analysis of conditional rank order proximity data. We present the technical aspects of the model and the estimation algorithm. Some preliminary Monte Carlo results are discussed. A consumer psychology application is provided examining the similarity of fifteen types of snack/breakfast items. Finally, some directions for future research are provided.

Original languageEnglish (US)
Pages (from-to)47-75
Number of pages29
JournalPsychometrika
Volume60
Issue number1
DOIs
StatePublished - Mar 1 1995

Fingerprint

Rank order
Proximity
Maximum likelihood
Snacks
Breakfast
Psychometrics
Estimation Algorithms
Discrete Model
Network Model
Maximum Likelihood
Monotone
Optimise
Psychology
Invariant
Model

All Science Journal Classification (ASJC) codes

  • Psychology(all)
  • Applied Mathematics

Cite this

Young, Martin R. ; Desarbo, Wayne. / A parametric procedure for ultrametric tree estimation from conditional rank order proximity data. In: Psychometrika. 1995 ; Vol. 60, No. 1. pp. 47-75.
@article{94156c70550e43d98de60fbef7ffbfb5,
title = "A parametric procedure for ultrametric tree estimation from conditional rank order proximity data",
abstract = "The psychometric and classification literatures have illustrated the fact that a wide class of discrete or network models (e.g., hierarchical or ultrametric trees) for the analysis of ordinal proximity data are plagued by potential degenerate solutions if estimated using traditional nonmetric procedures (i.e., procedures which optimize a STRESS-based criteria of fit and whose solutions are invariant under a monotone transformation of the input data). This paper proposes a new parametric, maximum likelihood based procedure for estimating ultrametric trees for the analysis of conditional rank order proximity data. We present the technical aspects of the model and the estimation algorithm. Some preliminary Monte Carlo results are discussed. A consumer psychology application is provided examining the similarity of fifteen types of snack/breakfast items. Finally, some directions for future research are provided.",
author = "Young, {Martin R.} and Wayne Desarbo",
year = "1995",
month = "3",
day = "1",
doi = "10.1007/BF02294429",
language = "English (US)",
volume = "60",
pages = "47--75",
journal = "Psychometrika",
issn = "0033-3123",
publisher = "Springer New York",
number = "1",

}

A parametric procedure for ultrametric tree estimation from conditional rank order proximity data. / Young, Martin R.; Desarbo, Wayne.

In: Psychometrika, Vol. 60, No. 1, 01.03.1995, p. 47-75.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A parametric procedure for ultrametric tree estimation from conditional rank order proximity data

AU - Young, Martin R.

AU - Desarbo, Wayne

PY - 1995/3/1

Y1 - 1995/3/1

N2 - The psychometric and classification literatures have illustrated the fact that a wide class of discrete or network models (e.g., hierarchical or ultrametric trees) for the analysis of ordinal proximity data are plagued by potential degenerate solutions if estimated using traditional nonmetric procedures (i.e., procedures which optimize a STRESS-based criteria of fit and whose solutions are invariant under a monotone transformation of the input data). This paper proposes a new parametric, maximum likelihood based procedure for estimating ultrametric trees for the analysis of conditional rank order proximity data. We present the technical aspects of the model and the estimation algorithm. Some preliminary Monte Carlo results are discussed. A consumer psychology application is provided examining the similarity of fifteen types of snack/breakfast items. Finally, some directions for future research are provided.

AB - The psychometric and classification literatures have illustrated the fact that a wide class of discrete or network models (e.g., hierarchical or ultrametric trees) for the analysis of ordinal proximity data are plagued by potential degenerate solutions if estimated using traditional nonmetric procedures (i.e., procedures which optimize a STRESS-based criteria of fit and whose solutions are invariant under a monotone transformation of the input data). This paper proposes a new parametric, maximum likelihood based procedure for estimating ultrametric trees for the analysis of conditional rank order proximity data. We present the technical aspects of the model and the estimation algorithm. Some preliminary Monte Carlo results are discussed. A consumer psychology application is provided examining the similarity of fifteen types of snack/breakfast items. Finally, some directions for future research are provided.

UR - http://www.scopus.com/inward/record.url?scp=21844495489&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=21844495489&partnerID=8YFLogxK

U2 - 10.1007/BF02294429

DO - 10.1007/BF02294429

M3 - Article

VL - 60

SP - 47

EP - 75

JO - Psychometrika

JF - Psychometrika

SN - 0033-3123

IS - 1

ER -