Valoración psicométrica del Cuestionario de Adicción a Redes Sociales (ARS) en adolescentes mexicanos

Psychometric assessment of the Social Media Addiction Questionnaire (ARS) in Mexican adolescents. With the increase in the use of the Internet, new phenomena have been appeared such as social media addiction, however, to delve into the subject and know the associated factors and consequences of this, it is necessary to have valid and reliable measurement instruments that allow to collect trustworthy information. The aim of this research was to obtain evidence on the factorial structure, validity, internal consistency, and measurement invariance across sex of the Social Media Addiction Questionnaire (ARS) in Mexican adolescents. 744 adolescents between 17 and 19 years of age (M = 17.52; SD = .58) who attended upper secondary level classes in a private high school in Mexico City participated. Of these 56.85% were women and 43.15% men. Item analyzes were carried out following the techniques proposed in the Classical Test Theory. After reviewing the distribution, discrimination, total item correlation and multicollinearity of the items, the psychometric properties of the instrument were tested. The original model made up for did not present an adequate adjustment in this population. Therefore, by means of an exploratory factor analysis and subsequent confirmatory factor analysis, a three-factor model was obtained, in which two factors of the original model are maintained and a new one emerges. The modification for the Mexican population is constituted by less than half of original items (11 out of 24). In this factorial structure adequate indices and internal consistency values were observed for both. The questionnaire shows metric, strong and strict measurement invariance between men and women. It is concluded that this version of the ARS scale has acceptable psychometric characteristic to evaluate Mexican adolescents from private schools, adding to the current tools for social media addiction research. Although it is necessary to gather more evidence of the psychometric properties of the instrument.