Factoring Items and Factoring Scales Are Different

Spurious Evidence for Multidimensionality Due to Item Categorization

Ira H. Bernstein, Gary Teng

Research output: Contribution to journalArticle

237 Citations (Scopus)

Abstract

Illustrates how categorization spuriously influences apparent dimensionality inferred from (a) principal components (PC), (b) exploratory maximum likelihood (EML) analysis, and (c) LISREL. Simulated continuous, parallel, unifactor "scores," of differing reliability, were categorized in various ways to creat "items." All forms of categorization spuriously suggested multidimensionality. PC-based indices were more misleading with less reliable data; the reverse was true with inferential (EML and LISREL) indices. Varying item "splits" to create item distribution differences further enhanced these spurious effects. Likewise, multicategory (Likert-type) items were more likely to yield artifacts than dichotomous items using inferential criteria even though the multicategory data were more reliable. Criteria for dimensionality applicable to continuous (scale-level) data are therefore inappropriate for discrete (item-level) data.

Original languageEnglish (US)
Pages (from-to)467-477
Number of pages11
JournalPsychological Bulletin
Volume105
Issue number3
StatePublished - May 1989

Fingerprint

Artifacts
Maximum Likelihood
Principal Components
Multidimensionality
Split
Artifact

ASJC Scopus subject areas

  • Psychology(all)
  • History and Philosophy of Science

Cite this

Factoring Items and Factoring Scales Are Different : Spurious Evidence for Multidimensionality Due to Item Categorization. / Bernstein, Ira H.; Teng, Gary.

In: Psychological Bulletin, Vol. 105, No. 3, 05.1989, p. 467-477.

Research output: Contribution to journalArticle

@article{360e192d54534e78a5b0609b033ffb89,
title = "Factoring Items and Factoring Scales Are Different: Spurious Evidence for Multidimensionality Due to Item Categorization",
abstract = "Illustrates how categorization spuriously influences apparent dimensionality inferred from (a) principal components (PC), (b) exploratory maximum likelihood (EML) analysis, and (c) LISREL. Simulated continuous, parallel, unifactor {"}scores,{"} of differing reliability, were categorized in various ways to creat {"}items.{"} All forms of categorization spuriously suggested multidimensionality. PC-based indices were more misleading with less reliable data; the reverse was true with inferential (EML and LISREL) indices. Varying item {"}splits{"} to create item distribution differences further enhanced these spurious effects. Likewise, multicategory (Likert-type) items were more likely to yield artifacts than dichotomous items using inferential criteria even though the multicategory data were more reliable. Criteria for dimensionality applicable to continuous (scale-level) data are therefore inappropriate for discrete (item-level) data.",
author = "Bernstein, {Ira H.} and Gary Teng",
year = "1989",
month = "5",
language = "English (US)",
volume = "105",
pages = "467--477",
journal = "Psychological Bulletin",
issn = "0033-2909",
publisher = "American Psychological Association Inc.",
number = "3",

}

TY - JOUR

T1 - Factoring Items and Factoring Scales Are Different

T2 - Spurious Evidence for Multidimensionality Due to Item Categorization

AU - Bernstein, Ira H.

AU - Teng, Gary

PY - 1989/5

Y1 - 1989/5

N2 - Illustrates how categorization spuriously influences apparent dimensionality inferred from (a) principal components (PC), (b) exploratory maximum likelihood (EML) analysis, and (c) LISREL. Simulated continuous, parallel, unifactor "scores," of differing reliability, were categorized in various ways to creat "items." All forms of categorization spuriously suggested multidimensionality. PC-based indices were more misleading with less reliable data; the reverse was true with inferential (EML and LISREL) indices. Varying item "splits" to create item distribution differences further enhanced these spurious effects. Likewise, multicategory (Likert-type) items were more likely to yield artifacts than dichotomous items using inferential criteria even though the multicategory data were more reliable. Criteria for dimensionality applicable to continuous (scale-level) data are therefore inappropriate for discrete (item-level) data.

AB - Illustrates how categorization spuriously influences apparent dimensionality inferred from (a) principal components (PC), (b) exploratory maximum likelihood (EML) analysis, and (c) LISREL. Simulated continuous, parallel, unifactor "scores," of differing reliability, were categorized in various ways to creat "items." All forms of categorization spuriously suggested multidimensionality. PC-based indices were more misleading with less reliable data; the reverse was true with inferential (EML and LISREL) indices. Varying item "splits" to create item distribution differences further enhanced these spurious effects. Likewise, multicategory (Likert-type) items were more likely to yield artifacts than dichotomous items using inferential criteria even though the multicategory data were more reliable. Criteria for dimensionality applicable to continuous (scale-level) data are therefore inappropriate for discrete (item-level) data.

UR - http://www.scopus.com/inward/record.url?scp=58149373040&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=58149373040&partnerID=8YFLogxK

M3 - Article

VL - 105

SP - 467

EP - 477

JO - Psychological Bulletin

JF - Psychological Bulletin

SN - 0033-2909

IS - 3

ER -