In recent years, network analysis has gathered increasing interest from psychologists using it as an alternative approach to identify and analyze emerging associative patterns of psychological variables. These applications have been made possible by the development of statistics and tests that allow both the description and the comparison of observed networks. Based on these considerations, the present work aimed to apply the psychometric network analysis to investigate the psychometric characteristics of the Italian version of the Short Mood and Feelings Questionnaire. A sample of 580 Italian adolescents (317 males, 263 females) aged 14–20 years completed the Short Mood and Feelings Questionnaire (SMFQ), a 13-item self-report scale used for depression screening. Preliminarily, the undirected network was estimated using the EBICglasso method, which estimates a Gaussian Graphical Model (GGM) by applying regularization to reduce spurious relationships. Subsequently, a comparative network analysis was performed to assess potential disparities in network characteristics between sex and age groups through testing network invariance. Descriptive analysis of the network that emerged on the total sample confirmed that the estimated network is dense, with almost all items related to each other, highlighting two indicators (i1 and i5) with greater centrality and one with the lowest centrality (i9). Subsequently, the comparison analysis of the network as a function of sex and age showed a substantial invariance (ps > 0.33), highlighting the presence of only one edge showing significant differences across males and females. Psychometric network analysis can be considered a useful approach to explore the relationships between the indicators of a construct, allowing not only to identify which have greater centrality but also to compare network structures to verify the invariance. Possible expansions and limitations of this application are discussed.
An Application of the Network Analysis to the Study of the Psychometric Properties of the Short Mood and Feeling Questionnaire
Catone, Gennaro;Senese, Vincenzo Paolo
2025-01-01
Abstract
In recent years, network analysis has gathered increasing interest from psychologists using it as an alternative approach to identify and analyze emerging associative patterns of psychological variables. These applications have been made possible by the development of statistics and tests that allow both the description and the comparison of observed networks. Based on these considerations, the present work aimed to apply the psychometric network analysis to investigate the psychometric characteristics of the Italian version of the Short Mood and Feelings Questionnaire. A sample of 580 Italian adolescents (317 males, 263 females) aged 14–20 years completed the Short Mood and Feelings Questionnaire (SMFQ), a 13-item self-report scale used for depression screening. Preliminarily, the undirected network was estimated using the EBICglasso method, which estimates a Gaussian Graphical Model (GGM) by applying regularization to reduce spurious relationships. Subsequently, a comparative network analysis was performed to assess potential disparities in network characteristics between sex and age groups through testing network invariance. Descriptive analysis of the network that emerged on the total sample confirmed that the estimated network is dense, with almost all items related to each other, highlighting two indicators (i1 and i5) with greater centrality and one with the lowest centrality (i9). Subsequently, the comparison analysis of the network as a function of sex and age showed a substantial invariance (ps > 0.33), highlighting the presence of only one edge showing significant differences across males and females. Psychometric network analysis can be considered a useful approach to explore the relationships between the indicators of a construct, allowing not only to identify which have greater centrality but also to compare network structures to verify the invariance. Possible expansions and limitations of this application are discussed.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
