Comparison of three computational procedures for ...
Object Details
View
Title Information
Comparison of three computational procedures for solving the number of factors problem in exploratory factor analysis
Comparison of three computational procedures for solving the number of factors problem in exploratory factor analysis
Name:Personal
Piccone, Adam Vincent Role :Text(marcrelator)
creator
Piccone, Adam Vincent Role :Text(marcrelator)
creator
Name:Personal
Mundfrom, Daniel J. Role :Text(marcrelator)
thesis advisor
Mundfrom, Daniel J. Role :Text(marcrelator)
thesis advisor
Name:Personal
Schaffer, Jay Role :Text
committee member
Schaffer, Jay Role :Text
committee member
Name:Personal
Perrett, Jamis Role :Text
committee member
Perrett, Jamis Role :Text
committee member
Name:Personal
Pulos, Steven Role :Text
committee member
Pulos, Steven Role :Text
committee member
Name:Corporate
Applied Statistics & Research Methods Role :Text(marcrelator)
sponsor
Applied Statistics & Research Methods Role :Text(marcrelator)
sponsor
Name:Corporate
University of Northern Colorado Role :Text(marcrelator)
degree grantor
University of Northern Colorado Role :Text(marcrelator)
degree grantor
typeOfResource
text genre(marcgt)
Thesis
Origin Information
Place
University of Northern Colorado (keyDate="yes")
2009-12 Place :Text
Greeley (Colo.)
2009-12
University of Northern Colorado (keyDate="yes")
2009-12 Place :Text
Greeley (Colo.)
2009-12
Language
:Text
English
English
Physical Description
141 pages
born digital
141 pages
born digital
abstract
Three computational solutions to the number of factors problem were investigated over a wide variety of typical psychometric situations using Monte Carlo simulated population matrices with known characteristics. The standard error scree, the minimum average partials test, and the technique of parallel analysis were evaluated head-to-head for accuracy. The question of using principal components-based eigenvalues versus common factors-based eigenvalues in the analyses was also investigated. As a benchmark, the commonly used eigenvalues-greater-than-one criterion was included. Across all conditions, the principal components-based version of parallel analysis was found to most accurately recover dimensionality using sample correlation matrices drawn from populations with known, simple factor structures. The high degree of accuracy observed for this method suggests that a workable solution to the age-old number of factors problem may be close at hand. note
[Released from 1 year embargo]
Subject
Statistics
Quantitative Psychology
Factor Analysis
Minimum Average Partial Test
Number of Factors
Parallel Analysis
Principal Component Analysis
Standard Error Scree Test
Statistics
Quantitative Psychology
Factor Analysis
Minimum Average Partial Test
Number of Factors
Parallel Analysis
Principal Component Analysis
Standard Error Scree Test
Related Item
:series
Related Item
:thesis(displayLabel="Degree Type")
Ph.D.
Ph.D.
Related Item
:thesis(displayLabel="Degree Name")
doctoral
doctoral
identifier:Local
Piccone_unco_0161N_10019.pdf
Location
(usage="primary display")
http://hdl.handle.net/10176/cogru:264
http://hdl.handle.net/10176/cogru:264
accessCondition:useAndReproduction
Copyright is held by the author.
Record Information
languageOfCataloging
:Text(ISO639-2B)
English :Code(ISO639-2B)
eng
English :Code(ISO639-2B)
eng
note:admin
note:bibliography
note:thesis(displayLabel="Degree Type")
PhD note:thesis(displayLabel="Degree Name")
doctoral
Subject
Subject
Subject
Name:Personal
Subject
Name:Corporate
Subject
accessCondition:restrictionOnAccess
Title Information:Alternative