Comparison of Factor Extraction Methods in Exploratory Factor Analysis and Their Impact on Model Quality

The study aims to compare three factor extraction methods in exploratory factor analysis—principal component analysis (PCA), principal axis factorization (PAF), and maximum likelihood (ML)—and to demonstrate the impact of these methods on factor structure and model quality indices. The study was conducted using survey data measuring satisfaction with teaching, consisting of ten items on a five-point Likert scale, collected from a sample of 400 students at the College of Management and Economics at the University of Kirkuk for the 2024–2025 academic year. The data were analyzed using SPSS Version 18, and the factor extraction methods were compared in terms of the number of extracted factors, the proportion of variance explained, communalities values, factor loadings, the interpretability of the factor structure, and fit indices where available. The results showed that three factors were extracted using each method, with differences in the proportion of variance explained, communalities values, and factor loadings. The principal components method achieved a higher proportion of total explained variance, while the principal axes and maximum likelihood methods focused on the variance shared among the variables. The maximum likelihood method also allowed for a statistical test of model fit. The study concluded that the choice between extraction methods should not be based on a single indicator, as the most appropriate method depends on the objective of the analysis; the principal components method is preferred when the goal is data reduction, while the principal axes and maximum likelihood methods are more suitable when seeking to uncover underlying factors. Thus, evaluating model quality requires consideration of the statistical objectives of each method and a set of integrated indicators.

Authors

Institutions

Publication Details

Journal
Paaua Science Journal
Published
2026-11-18
DOI
https://doi.org/10.65760/paaujs.v1i2.6
Primary Topic
Psychometric Methodologies and Testing
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Comparison of Factor Extraction Methods in Exploratory Factor Analysis and Their Impact on Model Quality

Omar Macky Rahim, Sazan Najat Najadeen., Enas Salah Khorshid
Paaua Science Journal
Psychometric Methodologies and Testing
article

Comparison of Factor Extraction Methods in Exploratory Factor Analysis and Their Impact on Model Quality

Omar Macky Rahim, Sazan Najat Najadeen., Enas Salah Khorshid
article en

Abstract

The study aims to compare three factor extraction methods in exploratory factor analysis—principal component analysis (PCA), principal axis factorization (PAF), and maximum likelihood (ML)—and to demonstrate the impact of these methods on factor structure and model quality indices. The study was conducted using survey data measuring satisfaction with teaching, consisting of ten items on a five-point Likert scale, collected from a sample of 400 students at the College of Management and Economics at the University of Kirkuk for the 2024–2025 academic year. The data were analyzed using SPSS Version 18, and the factor extraction methods were compared in terms of the number of extracted factors, the proportion of variance explained, communalities values, factor loadings, the interpretability of the factor structure, and fit indices where available. The results showed that three factors were extracted using each method, with differences in the proportion of variance explained, communalities values, and factor loadings. The principal components method achieved a higher proportion of total explained variance, while the principal axes and maximum likelihood methods focused on the variance shared among the variables. The maximum likelihood method also allowed for a statistical test of model fit. The study concluded that the choice between extraction methods should not be based on a single indicator, as the most appropriate method depends on the objective of the analysis; the principal components method is preferred when the goal is data reduction, while the principal axes and maximum likelihood methods are more suitable when seeking to uncover underlying factors. Thus, evaluating model quality requires consideration of the statistical objectives of each method and a set of integrated indicators.

Paaua Science JournalVol. 1(2)
University of Kirkuk (IQ)
Psychometric Methodologies and Testing
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon