2010
DOI: 10.1177/0013164410379332
|View full text |Cite
|
Sign up to set email alerts
|

Evaluation of Parallel Analysis Methods for Determining the Number of Factors

Abstract: Population and sample simulation approaches were used to compare the performance of parallel analysis using principal component analysis (PA-PCA) and parallel analysis using principal axis factoring (PA-PAF) to identify the number of underlying factors. Additionally, the accuracies of the mean eigenvalue and the 95th percentile eigenvalue criteria were examined. The 95th percentile criterion was preferable for assessing the first eigenvalue using either extraction method. In assessing subsequent eigenvalues, P… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

5
185
0
7

Year Published

2012
2012
2024
2024

Publication Types

Select...
7
1
1

Relationship

0
9

Authors

Journals

citations
Cited by 195 publications
(197 citation statements)
references
References 24 publications
5
185
0
7
Order By: Relevance
“…In order to determine the number of factors that should be extracted from the initial pool of items, a parallel analysis based on a polychoric matrix of correlations was chosen because it is a robust option to determine the number of factors in scales consisting of ordered polytomous items (Crawford et al, 2010;Holgado-Tello, Chacón-Moscoso, Barbero-García, & Vila-Abad, 2010;Lorenzo-Seva, Timmerman, & Kiers, 2011;. A polychoric correlation matrix of the initial set of items to be responded on a 7-point scale was subjected to an EFA performed with the extraction method of ordinary least squares.…”
Section: Study 1: Calibration Of the New Measurement Instrumentmentioning
confidence: 99%
“…In order to determine the number of factors that should be extracted from the initial pool of items, a parallel analysis based on a polychoric matrix of correlations was chosen because it is a robust option to determine the number of factors in scales consisting of ordered polytomous items (Crawford et al, 2010;Holgado-Tello, Chacón-Moscoso, Barbero-García, & Vila-Abad, 2010;Lorenzo-Seva, Timmerman, & Kiers, 2011;. A polychoric correlation matrix of the initial set of items to be responded on a 7-point scale was subjected to an EFA performed with the extraction method of ordinary least squares.…”
Section: Study 1: Calibration Of the New Measurement Instrumentmentioning
confidence: 99%
“…Sete fatores explicaram um total de 73,10% da variância, excedendo o nível mínimo de 60% para o desenvolvimento de escala (Hinkin, 1998). A análise paralela (Crawford et al, 2010) corroborou a extração de sete fatores. A matriz de correlação dos fatores mostrou correlações acima de 0,30 para os fatores encontrados, implicando que os fatores estão relacionados e são relativamente independentes um do outro (Tabachnick & Fidell, 2007).…”
Section: Resultados Da Afeunclassified
“…The results of both the Exploratory Graphical Analysis (EGA) and the Confi rmatory Factor Analysis (CFA) pointed to the appropriateness of a three-dimensional model. The contradictory result of the parallel analysis, which indicated the extraction of only two dimensions, can be explained by this method's limitations: It tends to minimize the number of dimensions of models with high correlations between factors and a small number of items per factor (Crawford et al, 2010;Golino & Epskamp, 2017;Ruscio & Roche, 2012).…”
Section: Discussionmentioning
confidence: 99%
“…EGA is a recently developed technique that uses network analysis coupled with algorithms to detect factors subjacent to the data. This technique is more accurate than parallel analysis for estimating the true number of factors, especially for structures with high correlations between factors and a small number of items per factor (Crawford et al, 2010;Golino & Epskamp, 2017;Ruscio & Roche, 2012).…”
Section: Data Analysis Proceduresmentioning
confidence: 99%