Comparison of Common Methods of Extraction and Rotation in Exploratory Factor Analysis to Validate the Addiction Potential Questionnaire of 12-18-Year-Old Iranian Children

Aboubakr  Jafarnezhad; Haleh Ghaem  Maralani; Ali  Sahraian; Jafar  Hassanzadeh

doi:10.18502/acta.v63i1.18592

Aboubakr Jafarnezhad Department of Epidemiology, Student Research Committee, School of Health, Shiraz University of Medical Sciences, Shiraz, Iran
Haleh Ghaem Maralani Department of Epidemiology, Non-Communicable Diseases Research Center, School of Health, Shiraz University of Medical Sciences, Shiraz, Iran
Ali Sahraian Department of Psychiatry, Research Center for Psychiatry and Behavioral Science, Shiraz University of Medical Sciences, Shiraz, Iran
Jafar Hassanzadeh Department of Epidemiology, Research Centre for Health Sciences, Institute of Health, School of Health, Shiraz University of Medical Sciences, Shiraz, Iran

DOI: https://doi.org/10.18502/acta.v63i1.18592

Keywords: Addiction potential questionnaire; Validation; Factor analysis; Rotations; Child; Iran

Abstract

The drug crisis, especially in children, is expanding as a global challenge. The purpose of this study was to compare extraction and rotation methods in exploratory factor analysis to validate the children's addiction potential questionnaire. This cross-sectional study was conducted in 2023 on 400 students from the city of Shiraz, Iran, using a multi-stage sampling method (stratified-cluster-simple random sampling). Inclusion Criteria: Participants were students residing in Shiraz and enrolled in the first or second year of high school. After designing the questions and assessing their face and content validity, as well as reliability (using Cronbach's alpha), the final questionnaire was administered to the participants. Exploratory factor analysis was performed using various extraction and rotation methods. The statistical methods used for analysis included descriptive-analytical indices, correlation coefficients, exploratory factor analysis, and Cronbach's alpha, utilizing SPSS software version 26. This research has received ethical approval under the code IR.SUMS.SCHEANUT.REC.1402.112. The mean age of participants was 15.39±1.94 years. The face and content validity (both quantitatively and qualitatively) as well as reliability (using Cronbach's alpha) were assessed and confirmed. The best extraction method was maximum likelihood, and the optimal rotation method was Varimax. The percentage of variance explained varied across different extraction methods, with the highest percentage being 39.5% for the Generalized Least Squares method and the lowest percentage being 25.8% for the Image Factoring method. The results indicate a suitable validation of the children’s addiction potential questionnaire. The careful selection of extraction and rotation methods based on the characteristics of the data and the research objectives plays a crucial role in achieving valid results. In this study, the best extraction method was found to be maximum likelihood, and the optimal rotation method was Varimax, resulting in the identification of four factors.