Adolescence is a transitional period from childhood to adulthood when significant biological and social developmental processes occur [1]. During this stage, adolescents’ health is particularly vulnerable to adversities associated with low socioeconomic status (SES), which can substantially increase the risk of poor health outcomes later in life [2,3]. Multiple factors related to material, behavioral, and psychosocial pathways have been identified in the relationship between SES and adolescent health [4,5]. However, recent data show that socioeconomic inequalities in adolescent health are increasing, highlighting the need for more research and relevant policies to address this critical public health issue, especially in countries with high levels of poverty and inequality [6].

Despite the common view that young people from low-SES families are more likely to have poor health compared to their peers from high-SES families, in a study conducted among British adolescents, West [7,8] observed little variation in various health measures across SES strata in the UK. Based on his findings, he proposed the equalization in health hypothesis, which suggests that the school environment, peers, and youth culture can substantially reduce social-class differences in adolescents’ health, particularly in relation to psychosocial health outcomes [7–9]. Further studies suggested that status hierarchies present in peer-group structures, such as created by academic success, sports achievements, popularity, respect, or being a trouble-maker, can compete with SES and suppress the SES-health gradient among adolescents [9–13].

Bullying perpetration might be an alternative way of hierarchy formation among adolescents. Perhaps having no other means to improve their status, adolescents can use bullying to gain power and establish a higher position in peer-group hierarchies, pushing victims down to the bottom of the hierarchy [14–17]. Evidence suggests that the rates of mental health problems in those adolescents are low [18–20]. Moreover, in a recent study among US adolescents, bullying perpetration predicted low levels of inflammatory markers in young adulthood, suggesting long-lasting positive health effects of bullying perpetration [21]. Considering that bullying perpetration is more common among low-SES adolescents [22–24], it can, as already implied by West, potentially suppress the socioeconomic inequalities in adolescents’ health. Furthermore, bullying perpetration might alternatively be looked at as a coping and compensatory strategy for the negative influences of low SES [25,26]. This would imply a weaker relationship between low SES and poor health in perpetrators than in non-perpetrators, a pattern of associations that perhaps especially can be found in settings with high poverty levels and insufficient anti-bullying measures.

Armenia is a middle-income country, with a third of the population living in poverty [27]. Recent research indicates that SES is strongly associated with adolescent health in the country [28]. Also, bullying has been reported to be a significant public health concern in Armenia, with a lack of measures to prevent it [29], which can result in severe and long-lasting mental health consequences for victims [14]. However, the way SES, bullying, and adolescent health relate or interact in Armenia has not been studied. Therefore, in this paper, we aimed to investigate the role of bullying perpetration in the relationship between SES and health among a nationally representative sample of 3679 adolescents participating in the Health Behavior in School-aged Children (HBSC) study. Based on the above-mentioned, we propose two hypotheses. Our first hypothesis is that controlling for bullying perpetration increases the magnitude of the relationship between low SES and poor health, indicating that the influence of low SES on poor health is suppressed by bullying perpetration. The second hypothesis is that socioeconomic inequalities in health are substantially weaker in bullies, suggesting that bullying perpetration, as an alternative hierarchy, compensates for the negative health influence of low SES.

In this study, 13.6% of students reported at least one episode of bullying perpetration in the past couple of months. The majority of perpetrators were boys (72.9%), younger than 15 years of age (80.5%), and were more likely to be bullied themselves compared to non-perpetrators (29.1% vs. 5.3%, P < 0.001). However, there was no statistically significant relationship (P > 0.05) between bullying perpetration and the SES measures (Table 1). Bullying perpetration was not associated with less than good health (OR = 1.14, 95% CI = 0.88–1.47) or low psychosocial well-being (OR = 0.96, 95% CI = 0.76–1.20) but increased the likelihood of reporting high levels of psychosomatic symptoms (OR = 2.19, 95% CI = 1.71–2.81). Bullying victimization was consistently associated with increased odds of poor health outcomes (not tabulated). The effect of bullying perpetration did not depend on victim status (P-interaction > 0.05).

In Model 1, adjusted for age, sex, and bullying victimization, both low family SEP and low material well-being were strongly associated with poor health outcomes, except for the relationship between low material well-being and high psychosomatic symptoms (Table 2). The relationship between bullying perpetration and adolescent health were non-significant (P > 0.05) for less than good health and low psychosocial well-being but remained significant (P < 0.05) for high psychosomatic symptoms. Bullying victimization significantly (P < 0.05) increased the likelihood of reporting poor health outcomes (not tabulated).

Adding bullying perpetration to Model 1 did not change the SES-health gradient substantially (Table 2). However, in stratified analyses, the SES-health relationships were consistently weaker among perpetrators than non-perpetrators (Table 3). The largest observed difference was in the relationship between low family SEP and less than good health (OR = 3.60, 95% CI = 2.77–4.67 vs. OR = 1.80, 95% CI = 1.06–3.04), and the smallest difference was in the relationship between low family SEP and high psychosomatic symptoms (OR = 1.27, 95% CI = 1.03–1.56 vs. OR = 1.04, 95% CI = 0.61–1.77).

To interpret the interaction above, the same model results were reproduced by presenting the relationships between bullying perpetration and poor health outcomes for low- and high-SES adolescents separately (S1 Table). In adolescents from low-SES families, bullying perpetration was significantly or apparently associated with better perceived health status, higher psychosocial well-being, and fewer psychosomatic symptoms. In adolescents from high-SES families, bullying perpetration was associated with increased odds of reporting poor health outcomes. No consistent and conclusive sex differences in the relationship between low-SES measures, bullying perpetration, and poor health outcomes were revealed.

We used data from the HBSC 2013/14 survey to assess the role of bullying in the relationship between SES and health among a nationally representative sample of Armenian adolescents. Contrary to previous research [22–24], bullying perpetration was not associated with low-SES measures in the present study, suggesting a context-depended and possibly multifactorial relationship between SES and bullying perpetration. As a result, adding bullying perpetration to the models did not change the magnitude of the association between low SES and poor health. Therefore, we could not support our first hypothesis that the relationship between low SES and poor health was suppressed by bullying perpetration. However, we found that socioeconomic inequalities in health were weaker among perpetrators, providing evidence for our second hypothesis, that bullying perpetration, as an alternative hierarchy, may compensate for the adverse health effects of low SES in adolescents.

In this study, bullying perpetration was significantly or apparently associated with better perceived health status, better psychosocial well-being, and fewer psychosomatic symptoms in adolescents from low-SES families. Our findings are consistent with the low-status compensation theory [25,26], which suggests that low-SES individuals might use violence to compensate for their low status. Although undesirable, it appears that Armenian adolescents from low-SES families might use bullying perpetration to achieve higher status among their peers, which can make them feel better, whether through improved control and social participation [34] or relieved status anxiety [35]. More research into this (perpetration) and other (perhaps ethically more accepted) coping/compensatory strategies to handle the vicious health-compromising influence of socioeconomic stratification are needed. Qualitative research might provide more insight into the experiences, attitudes, and adaptive strategies of adolescents.

In the present study, we also found that bullying perpetration can be associated with poor health outcomes in adolescents from high-SES families. Research has demonstrated that high-SES children might have a greater degree of achievement pressure, as well as emotional and physical isolation from their parents, which can cause psychosocial maladjustment and internalizing health problems, such as anxiety and depression [36,37], with the potential to create a downward spiral of isolation, maladjustment, and internalizing problems. A growing body of evidence suggests that maladjustment and internalizing issues might predict bullying perpetration [17,38–41], and therefore, it could have increased the risk of perpetrating bullying among high-SES adolescents. Further research is needed to explore this possibility.

There are several limitations to our study. The cross-sectional design makes it difficult to establish a causal relationship because of the possibility of reversed associations between bullying perpetration and poor health in high-SES adolescents. Adolescents might have underreported bullying perpetration because of social desirability bias. Therefore, the association between bullying perpetration and health might be underestimated, perhaps to a greater extent in the high-SES group. Although some of the relationships did not reach statistical significance (P < 0.05), our findings were consistent across all health outcomes and SES measures, suggesting robust associations between bullying perpetration and socioeconomic inequalities in health. Approximately 21.9% of adolescents had at least one missing responses related to psychosomatic complaints. However, this might have minimal impact on our results since the proportion of missing values was similar for high and low categories of the SES measures. For other variables, the proportions of respondents with missing data were relatively small (up to 8.6%).

In conclusion, the relationship between low SES and poor health was weaker in bullying perpetrators, suggesting that bullying perpetration, as an alternative hierarchy, may be looked at as a compensatory, but vicious strategy in the face of the negative health influences of low SES in Armenian adolescents. Context-specific drivers of bullying perpetration are poorly studied in Armenia. Unfortunately, for adolescents from low-SES families, bullying can be a way to achieve a higher position in the peer hierarchy and feel better, whether through improved control and social participation or relieved status anxiety. For high-SES adolescents, on the other hand, social, emotional, or psychological problems may increase the risk of bullying perpetration. Hence, healthier alternatives to bullying perpetration should be encouraged, especially for adolescents from low-SES families. Targeted health interventions might be necessary for high-SES perpetrators. Consequently, bullying prevention activities in Armenia should focus on both low and high-SES adolescents, considering SES-specific pathways and mechanisms. Further studies are needed to identify the contextual factors and the underlying mechanisms for the observed complex relationships between family SES, bullying perpetration, and adolescent health.