A Proposed Solution to the Problem With Using Completely Random Data to Assess the Number of Factors With Parallel Analysis

Samuel B. Green, Roy Levy, Marilyn S. Thompson, Min Lu, Wen Juo Lo

Research output: Contribution to journalArticle

22 Citations (Scopus)

Abstract

A number of psychometricians have argued for the use of parallel analysis to determine the number of factors. However, parallel analysis must be viewed at best as a heuristic approach rather than a mathematically rigorous one. The authors suggest a revision to parallel analysis that could improve its accuracy. A Monte Carlo study is conducted to compare revised and traditional parallel analysis approaches. Five dimensions are manipulated in the study: number of observations, number of factors, number of measured variables, size of the factor loadings, and degree of correlation between factors. Based on the results, the revised parallel analysis method, using principal axis factoring and the 95th percentile eigenvalue rule, offers promise.

Original languageEnglish (US)
Pages (from-to)357-374
Number of pages18
JournalEducational and Psychological Measurement
Volume72
Issue number3
DOIs
StatePublished - Jun 2012

Fingerprint

factoring
Percentile
Factoring
Monte Carlo Study
heuristics
Heuristics
Eigenvalue
Observation

Keywords

  • factor analysis
  • number of factors
  • parallel analysis

ASJC Scopus subject areas

  • Algebra and Number Theory
  • Psychology(all)
  • Developmental and Educational Psychology
  • Psychology (miscellaneous)
  • Education

Cite this

A Proposed Solution to the Problem With Using Completely Random Data to Assess the Number of Factors With Parallel Analysis. / Green, Samuel B.; Levy, Roy; Thompson, Marilyn S.; Lu, Min; Lo, Wen Juo.

In: Educational and Psychological Measurement, Vol. 72, No. 3, 06.2012, p. 357-374.

Research output: Contribution to journalArticle

@article{55ea510aec794207a25b3589709756fb,
title = "A Proposed Solution to the Problem With Using Completely Random Data to Assess the Number of Factors With Parallel Analysis",
abstract = "A number of psychometricians have argued for the use of parallel analysis to determine the number of factors. However, parallel analysis must be viewed at best as a heuristic approach rather than a mathematically rigorous one. The authors suggest a revision to parallel analysis that could improve its accuracy. A Monte Carlo study is conducted to compare revised and traditional parallel analysis approaches. Five dimensions are manipulated in the study: number of observations, number of factors, number of measured variables, size of the factor loadings, and degree of correlation between factors. Based on the results, the revised parallel analysis method, using principal axis factoring and the 95th percentile eigenvalue rule, offers promise.",
keywords = "factor analysis, number of factors, parallel analysis",
author = "Green, {Samuel B.} and Roy Levy and Thompson, {Marilyn S.} and Min Lu and Lo, {Wen Juo}",
year = "2012",
month = "6",
doi = "10.1177/0013164411422252",
language = "English (US)",
volume = "72",
pages = "357--374",
journal = "Educational and Psychological Measurement",
issn = "0013-1644",
publisher = "SAGE Publications Inc.",
number = "3",

}

TY - JOUR

T1 - A Proposed Solution to the Problem With Using Completely Random Data to Assess the Number of Factors With Parallel Analysis

AU - Green, Samuel B.

AU - Levy, Roy

AU - Thompson, Marilyn S.

AU - Lu, Min

AU - Lo, Wen Juo

PY - 2012/6

Y1 - 2012/6

N2 - A number of psychometricians have argued for the use of parallel analysis to determine the number of factors. However, parallel analysis must be viewed at best as a heuristic approach rather than a mathematically rigorous one. The authors suggest a revision to parallel analysis that could improve its accuracy. A Monte Carlo study is conducted to compare revised and traditional parallel analysis approaches. Five dimensions are manipulated in the study: number of observations, number of factors, number of measured variables, size of the factor loadings, and degree of correlation between factors. Based on the results, the revised parallel analysis method, using principal axis factoring and the 95th percentile eigenvalue rule, offers promise.

AB - A number of psychometricians have argued for the use of parallel analysis to determine the number of factors. However, parallel analysis must be viewed at best as a heuristic approach rather than a mathematically rigorous one. The authors suggest a revision to parallel analysis that could improve its accuracy. A Monte Carlo study is conducted to compare revised and traditional parallel analysis approaches. Five dimensions are manipulated in the study: number of observations, number of factors, number of measured variables, size of the factor loadings, and degree of correlation between factors. Based on the results, the revised parallel analysis method, using principal axis factoring and the 95th percentile eigenvalue rule, offers promise.

KW - factor analysis

KW - number of factors

KW - parallel analysis

UR - http://www.scopus.com/inward/record.url?scp=84864816565&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84864816565&partnerID=8YFLogxK

U2 - 10.1177/0013164411422252

DO - 10.1177/0013164411422252

M3 - Article

VL - 72

SP - 357

EP - 374

JO - Educational and Psychological Measurement

JF - Educational and Psychological Measurement

SN - 0013-1644

IS - 3

ER -