Rotation to a partially specified target matrix in exploratory factor analysis in practice

Nicholas Myers, Ying Jin, Soyeon Ahn, Seniz Celimli, Cengiz Zopluoglu

Research output: Contribution to journalArticle

10 Citations (Scopus)

Abstract

The purpose of the present study was to explore the influence of the number of targets specified on the quality of exploratory factor analysis solutions with a complex underlying structure and incomplete substantive measurement theory. We extended previous research in this area by (a) exploring this phenomenon in situations in which both the common factor model and the targeted pattern matrix contained specification errors and (b) comparing the performance of target rotation to an easier-to-use default rotation criterion (i.e., geomin) under conditions commonly observed in practice. A Monte Carlo study manipulated target error, number of targets, model error, overdetermination, communality, and sample size. Outcomes included bias (i.e., accuracy) and variability (i.e., stability) with regard to the rotated pattern matrix. The effects of target error were negligible for both accuracy and stability, whereas small effects were observed for the number of targets for both outcomes. Further, target rotation outperformed geomin rotation with regard to accuracy but generally performed worse than geomin rotation with regard to stability. These findings underscore the potential importance (or caution, in the case of stability) of using extant, even if incomplete and somewhat inaccurate, substantive measurement theory to inform the rotation criterion in a nonmechanical way.

Original languageEnglish (US)
Pages (from-to)494-505
Number of pages12
JournalBehavior Research Methods
Volume47
Issue number2
DOIs
StatePublished - Jun 1 2015

Fingerprint

Statistical Factor Analysis
Sample Size
Factor Analysis
Research

Keywords

  • Exploratory structural equation modeling
  • Model error
  • Monte Carlo
  • Simulation
  • Target error

ASJC Scopus subject areas

  • Psychology(all)
  • Psychology (miscellaneous)
  • Experimental and Cognitive Psychology
  • Arts and Humanities (miscellaneous)
  • Developmental and Educational Psychology

Cite this

Rotation to a partially specified target matrix in exploratory factor analysis in practice. / Myers, Nicholas; Jin, Ying; Ahn, Soyeon; Celimli, Seniz; Zopluoglu, Cengiz.

In: Behavior Research Methods, Vol. 47, No. 2, 01.06.2015, p. 494-505.

Research output: Contribution to journalArticle

@article{c9a18cc2612b432fb02d659a525308e5,
title = "Rotation to a partially specified target matrix in exploratory factor analysis in practice",
abstract = "The purpose of the present study was to explore the influence of the number of targets specified on the quality of exploratory factor analysis solutions with a complex underlying structure and incomplete substantive measurement theory. We extended previous research in this area by (a) exploring this phenomenon in situations in which both the common factor model and the targeted pattern matrix contained specification errors and (b) comparing the performance of target rotation to an easier-to-use default rotation criterion (i.e., geomin) under conditions commonly observed in practice. A Monte Carlo study manipulated target error, number of targets, model error, overdetermination, communality, and sample size. Outcomes included bias (i.e., accuracy) and variability (i.e., stability) with regard to the rotated pattern matrix. The effects of target error were negligible for both accuracy and stability, whereas small effects were observed for the number of targets for both outcomes. Further, target rotation outperformed geomin rotation with regard to accuracy but generally performed worse than geomin rotation with regard to stability. These findings underscore the potential importance (or caution, in the case of stability) of using extant, even if incomplete and somewhat inaccurate, substantive measurement theory to inform the rotation criterion in a nonmechanical way.",
keywords = "Exploratory structural equation modeling, Model error, Monte Carlo, Simulation, Target error",
author = "Nicholas Myers and Ying Jin and Soyeon Ahn and Seniz Celimli and Cengiz Zopluoglu",
year = "2015",
month = "6",
day = "1",
doi = "10.3758/s13428-014-0486-7",
language = "English (US)",
volume = "47",
pages = "494--505",
journal = "Behavior Research Methods",
issn = "1554-351X",
publisher = "Springer New York",
number = "2",

}

TY - JOUR

T1 - Rotation to a partially specified target matrix in exploratory factor analysis in practice

AU - Myers, Nicholas

AU - Jin, Ying

AU - Ahn, Soyeon

AU - Celimli, Seniz

AU - Zopluoglu, Cengiz

PY - 2015/6/1

Y1 - 2015/6/1

N2 - The purpose of the present study was to explore the influence of the number of targets specified on the quality of exploratory factor analysis solutions with a complex underlying structure and incomplete substantive measurement theory. We extended previous research in this area by (a) exploring this phenomenon in situations in which both the common factor model and the targeted pattern matrix contained specification errors and (b) comparing the performance of target rotation to an easier-to-use default rotation criterion (i.e., geomin) under conditions commonly observed in practice. A Monte Carlo study manipulated target error, number of targets, model error, overdetermination, communality, and sample size. Outcomes included bias (i.e., accuracy) and variability (i.e., stability) with regard to the rotated pattern matrix. The effects of target error were negligible for both accuracy and stability, whereas small effects were observed for the number of targets for both outcomes. Further, target rotation outperformed geomin rotation with regard to accuracy but generally performed worse than geomin rotation with regard to stability. These findings underscore the potential importance (or caution, in the case of stability) of using extant, even if incomplete and somewhat inaccurate, substantive measurement theory to inform the rotation criterion in a nonmechanical way.

AB - The purpose of the present study was to explore the influence of the number of targets specified on the quality of exploratory factor analysis solutions with a complex underlying structure and incomplete substantive measurement theory. We extended previous research in this area by (a) exploring this phenomenon in situations in which both the common factor model and the targeted pattern matrix contained specification errors and (b) comparing the performance of target rotation to an easier-to-use default rotation criterion (i.e., geomin) under conditions commonly observed in practice. A Monte Carlo study manipulated target error, number of targets, model error, overdetermination, communality, and sample size. Outcomes included bias (i.e., accuracy) and variability (i.e., stability) with regard to the rotated pattern matrix. The effects of target error were negligible for both accuracy and stability, whereas small effects were observed for the number of targets for both outcomes. Further, target rotation outperformed geomin rotation with regard to accuracy but generally performed worse than geomin rotation with regard to stability. These findings underscore the potential importance (or caution, in the case of stability) of using extant, even if incomplete and somewhat inaccurate, substantive measurement theory to inform the rotation criterion in a nonmechanical way.

KW - Exploratory structural equation modeling

KW - Model error

KW - Monte Carlo

KW - Simulation

KW - Target error

UR - http://www.scopus.com/inward/record.url?scp=84939893068&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84939893068&partnerID=8YFLogxK

U2 - 10.3758/s13428-014-0486-7

DO - 10.3758/s13428-014-0486-7

M3 - Article

C2 - 24903693

AN - SCOPUS:84939893068

VL - 47

SP - 494

EP - 505

JO - Behavior Research Methods

JF - Behavior Research Methods

SN - 1554-351X

IS - 2

ER -