When Does Rejection Trigger Aggression? A Test of the Multimotive Model

Abstract

Research has sought to identify the conditions under which rejection leads to retaliation. The Multimotive Model (MMM) proposes that there are three primary behavioral responses to rejection: prosocial (e.g., befriending others), asocial (e.g., withdrawal), and antisocial behavior (e.g., aggression toward others). In this study, we conducted the first full test of the MMM as well as expanded the model. Based on research linking aggression and "perceived groupness," construal items were added assessing whether the rejection was perceived as extending beyond the individual to one's peers. We also included self-harm behavioral responses as this outcome was not sufficiently captured by existing antisocial or asocial operationalizations. This expanded model was then tested with two high school student samples (Ns of 231 and 374) who reported experiencing aggressive rejection (i.e., experienced physical, verbal, relational, or cyber aggression from peers). The MMM was compared to a saturated model separately in each of the two datasets using structural equation modeling. Results indicate that the saturated model provides a better fit for the data than the MMM across all models examined (all p < 0.001). In part, this is due to certain paths having different associations than hypothesized. For example, perceiving the rejection as carrying a higher cost was predicted to promote prosocial behavior, where instead it predicted asocial responses. Perceived groupness was the strongest predictor of antisocial responses. Self-harm outcomes were significantly and consistently associated with higher perceived costs across the models. These results and others will be discussed in the context of how we can better encourage prosocial and discourage antisocial and self-harm responses to social rejection, including bullying.

Keywords: aggression; antisocial behavior; asocial behavior; bullying; perceived groupness; prosocial behavior; rejection; self-harm.

Figure 1

The modified multimotive model-predictions based on the multimotive model including anticipated groupness effect. Solid lines represents anticipated positive relationships. Dashed lines anticipated negative relaionships. Yellow lines and boxes were additions to the multimodel based on work on bullycide and perceivedgroupness effects.

Figure 2

Structural paths and covariances between latent variables are shown in the model, but not measurement paths. Paths estimated in both the Multimotive Model and saturated model are solid. Blue lines indicate a path that was restricted to be positive in the Multimotive Model and orange lines indicate a path that was restricted to be negative. Dotted lines indicate a path was only estimated in the saturated model.