Penalized Likelihood Principal Component Rotation for Enhanced Interpretation

Research output: Contribution to journalArticle

Abstract

Principal component analysis provides a ready exploratory tool for multivariate data when a priori models are unavailable. The objective is to assign interpretations to the components that provide intuition and serve as a guide for further exploration. However, principal components based on small samples are subject to high sampling variation that can obscure straightforward interpretations. Ad hoc techniques like Varimax rotation can enhance interpretability, at the expense of possibly losing fidelity to the data. These problems are alleviated if rotation criteria are instead used as penalty functions in a maximum penalized likelihood setting. Advantageous features of this approach include a smooth continuum of possible rotations, preferential rotation of components that are poorly defined, and a way to measure fidelity of rotated components to the data. Some computational challenges inherent in this technique have been alleviated by recent developments in algorithms for optimization subject to orthogonality constraints.

Original languageEnglish (US)
Pages (from-to)385-398
Number of pages14
JournalAmerican Journal of Mathematical and Management Sciences
Volume28
Issue number3-4
DOIs
StatePublished - Jan 1 2008
Externally publishedYes

Fingerprint

Penalized Likelihood
Principal Components
Fidelity
Penalized Maximum Likelihood
Interpretability
Multivariate Data
Penalty Function
Orthogonality
Small Sample
Principal component analysis
Principal Component Analysis
Maximum likelihood
Assign
Continuum
Sampling
Interpretation
Principal components
Optimization

Keywords

  • Lasso
  • Simplification
  • Varimax

ASJC Scopus subject areas

  • Business, Management and Accounting(all)
  • Applied Mathematics

Cite this

Penalized Likelihood Principal Component Rotation for Enhanced Interpretation. / Park, Trevor H.

In: American Journal of Mathematical and Management Sciences, Vol. 28, No. 3-4, 01.01.2008, p. 385-398.

Research output: Contribution to journalArticle

@article{5b89b850e23e4a76b420fd8ad7d9704b,
title = "Penalized Likelihood Principal Component Rotation for Enhanced Interpretation",
abstract = "Principal component analysis provides a ready exploratory tool for multivariate data when a priori models are unavailable. The objective is to assign interpretations to the components that provide intuition and serve as a guide for further exploration. However, principal components based on small samples are subject to high sampling variation that can obscure straightforward interpretations. Ad hoc techniques like Varimax rotation can enhance interpretability, at the expense of possibly losing fidelity to the data. These problems are alleviated if rotation criteria are instead used as penalty functions in a maximum penalized likelihood setting. Advantageous features of this approach include a smooth continuum of possible rotations, preferential rotation of components that are poorly defined, and a way to measure fidelity of rotated components to the data. Some computational challenges inherent in this technique have been alleviated by recent developments in algorithms for optimization subject to orthogonality constraints.",
keywords = "Lasso, Simplification, Varimax",
author = "Park, {Trevor H}",
year = "2008",
month = "1",
day = "1",
doi = "10.1080/01966324.2008.10737734",
language = "English (US)",
volume = "28",
pages = "385--398",
journal = "American Journal of Mathematical and Management Sciences",
issn = "0196-6324",
publisher = "American Sciences Press Inc.",
number = "3-4",

}

TY - JOUR

T1 - Penalized Likelihood Principal Component Rotation for Enhanced Interpretation

AU - Park, Trevor H

PY - 2008/1/1

Y1 - 2008/1/1

N2 - Principal component analysis provides a ready exploratory tool for multivariate data when a priori models are unavailable. The objective is to assign interpretations to the components that provide intuition and serve as a guide for further exploration. However, principal components based on small samples are subject to high sampling variation that can obscure straightforward interpretations. Ad hoc techniques like Varimax rotation can enhance interpretability, at the expense of possibly losing fidelity to the data. These problems are alleviated if rotation criteria are instead used as penalty functions in a maximum penalized likelihood setting. Advantageous features of this approach include a smooth continuum of possible rotations, preferential rotation of components that are poorly defined, and a way to measure fidelity of rotated components to the data. Some computational challenges inherent in this technique have been alleviated by recent developments in algorithms for optimization subject to orthogonality constraints.

AB - Principal component analysis provides a ready exploratory tool for multivariate data when a priori models are unavailable. The objective is to assign interpretations to the components that provide intuition and serve as a guide for further exploration. However, principal components based on small samples are subject to high sampling variation that can obscure straightforward interpretations. Ad hoc techniques like Varimax rotation can enhance interpretability, at the expense of possibly losing fidelity to the data. These problems are alleviated if rotation criteria are instead used as penalty functions in a maximum penalized likelihood setting. Advantageous features of this approach include a smooth continuum of possible rotations, preferential rotation of components that are poorly defined, and a way to measure fidelity of rotated components to the data. Some computational challenges inherent in this technique have been alleviated by recent developments in algorithms for optimization subject to orthogonality constraints.

KW - Lasso

KW - Simplification

KW - Varimax

UR - http://www.scopus.com/inward/record.url?scp=67650385632&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=67650385632&partnerID=8YFLogxK

U2 - 10.1080/01966324.2008.10737734

DO - 10.1080/01966324.2008.10737734

M3 - Article

AN - SCOPUS:67650385632

VL - 28

SP - 385

EP - 398

JO - American Journal of Mathematical and Management Sciences

JF - American Journal of Mathematical and Management Sciences

SN - 0196-6324

IS - 3-4

ER -