A Four-Wave Cross-Lagged Study of Exposure to Violent Contexts, Cognitive Distortions, and School Bullying during Adolescence

Abstract

School bullying represents a widespread expression of violence in the peer context. Guided by the social-ecological model, this study investigated the longitudinal and transactional pathways linking domestic and neighborhood/community violence exposure (through direct victimization and witnessing), self-serving cognitive distortions (CDs), and school bullying perpetration. Furthermore, consistent with the previous literature, we tested the cognitive desensitization process that could develop in response to chronically violent contexts. Two four-wave cross-lagged panel mediation models were tested in a sample of 778 high school students (28.1% males; M_age [Time 1; T1] = 14.20, SD = 0.58). The results showed differential effects of multiple contexts and forms of violence exposure, with domestic violence victimization and community violence witnessing being associated with self-serving CDs and bullying perpetration over time. Moreover, significant associations between CDs and bullying perpetration over time were found, with bidirectional effects for each of these longitudinal patterns. Finally, self-serving CDs significantly mediated the relationships between both domestic violence victimization and community violence witnessing and school bullying perpetration. These findings highlight the need to consider school bullying as a social phenomenon stemming from a complex and bidirectional interplay between individuals and the environments they inhabit, confirming a basic postulate that "violence breeds violence".

Keywords: adolescence; bullying perpetration; community violence exposure; domestic violence exposure; self-serving cognitive distortions.

Figure 1

Cross-lagged mediational model with domestic violence exposure as a witness and as a victim. Reported coefficients refer to standardized estimates. Bold lines represent significant indirect paths. For the sake of simplicity, nonsignificant paths and relations with control variables are omitted. †, represents statistically significant differences in paths across time. * p < 0.05, ** p < 0.01, *** p < 0.001.

Figure 2

Cross-lagged mediational model with community violence exposure as a witness and as a victim. Reported coefficients refer to standardized estimates. Bold lines represent significant indirect paths. For the sake of simplicity, nonsignificant paths and relations with control variables are omitted. †, represents statistically significant differences in paths across time. * p < 0.05, ** p < 0.01, *** p < 0.001.