Investigation of the Measurment Invairance of the Social Media Addiction Scale

Abstract

This study aims to examine the measurement invariance of the Social Media Addiction Scale (SMAS) in terms of gender, time spent on social media accounts, and the number of social media accounts. Invariance analyses conducted within the scope of the research were carried out on 672 participants. Measurement invariance studies were examined separately for all measurement models presented in SMAS and for each sub-factor in the scale. As a result of the analyses, it was revealed that the psychometric properties obtained from the measurement model may show bias according to the relevant subgroups for the SMAS, in cases where the model fits up to the configural and metric stages. Comparison of the scores obtained from this measurement tool can be made, but careful interpretation should be made, keeping in mind that the items may behave biased according to gender on an item basis. For the SMAS, it has been demonstrated that in cases where the model fits up to the configural, metric, and scalar invariance stages, comparisons of the psychometric properties obtained from the measurement model can be made without bias according to the relevant subgroups. In addition, in cases where scalar invariance is met, the scores obtained from the measurement tool can be compared and comments can be made on an item basis according to the relevant subgroups. Finally, it could be stated that any comparison made according to the subgroups tested using the SMAS would be meaningless in cases where even configural invariance is not accepted.