2014
DOI: 10.6018/analesps.30.3.199991
|View full text |Cite
|
Sign up to set email alerts
|

El análisis factorial exploratorio de los ítems: algunas consideraciones adicionales

Abstract: Resumen: El presente artículo puede considerarse como una ampliación al trabajo de Lloret et al. (2014) en la que se discuten, de forma ampliada, dos tópicos de especial relevancia en análisis factorial de ítems: (a) la decisión acerca de la matriz de correlación más apropiada en cada caso, y (b) la determinación de soluciones finales semi-confirmatorias, que sean realistas, interpretables y que utilicen la información disponible por el investigador. La presentación de los dos tópicos no es neutral, sino que r… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
63
0
74

Year Published

2017
2017
2024
2024

Publication Types

Select...
9

Relationship

2
7

Authors

Journals

citations
Cited by 124 publications
(138 citation statements)
references
References 27 publications
0
63
0
74
Order By: Relevance
“…Furthermore, given that the test is not too long and the sample is reasonably large, we considered that the best choice was to use the underlying-variables approach, and fit the Factor Analysis (FA) model to the inter-item polychoric correlation matrix (see Ferrando & Lorenzo-Seva, 2014). In this approach what we are fitting is Samejima's (1969) normal-ogive graded response model using an FA parameterization.…”
Section: Statistical Analysesmentioning
confidence: 99%
“…Furthermore, given that the test is not too long and the sample is reasonably large, we considered that the best choice was to use the underlying-variables approach, and fit the Factor Analysis (FA) model to the inter-item polychoric correlation matrix (see Ferrando & Lorenzo-Seva, 2014). In this approach what we are fitting is Samejima's (1969) normal-ogive graded response model using an FA parameterization.…”
Section: Statistical Analysesmentioning
confidence: 99%
“…We chose a method of Ordinary Least Squares. Ferrando and Lorenzo-Seva (2014) mention that the Minimum Averange Partial (MAP) method is the procedure that works best to determine the number of dimensions. Lloret-Segura et al (2014) says that for the estimation of factors, the Unweighted Least Squares method is currently the most recommended.…”
Section: Resultsmentioning
confidence: 99%
“…The procedure chosen to determine the number of dimensions was MAP, since it guarantees the estimation of all matrix correlations and leads to plausible estimates in all of them even in small samples (Ferrando and Lorenzo-Seva, 2014). The results of the analysis suggested that 2 were the factors to be retained in the factor solution.…”
Section: Descriptive Of the Scale Of Normative-moral Commitmentmentioning
confidence: 98%
“…Esto se debe a que el AFC parte del supuesto de que cada ítem es una medida factorialmente simple de un rasgo, es decir, que no es afectado por los demás factores. Ello es una suposición poco realista en los modelos de personalidad (Ferrando & Lorenzo-Seva, 2000), más aún el de los 5GF (McCrae, Zonderman, Costa Jr., Bond & Paunonen, 1996), porque existe evidencia de que los ítems tienden a la complejidad factorial (Ferrando & Lorenzo-Seva, 2014) y solo en ocasiones se acercan a una estructura factorialmente simple (Kaiser, 1974). Asimismo, no hay razones conceptuales que indiquen que las cargas factoriales en los factores secundarios sean cero en el modelo de los 5GF (McCrae et al, 1996), por lo que es necesario un procedimiento más de acuerdo con las bases conceptuales de un modelo que admita varianza compartida entre varios de sus factores (Aluja, García, García & Seisdedos, 2005;García, Escorial, García, Blanch & Aluja, 2012;Yang, 2010).…”
Section: Estrategias Analítico-factoriales Asociadas Al Estudio De Lounclassified