Potential moderators of effects in the actor–partner interdependence model (APIM) include variables that vary within dyads, between dyads, or both between and within dyads (i.e., mixed moderators). Another factor in the moderation of the APIM is whether dyads are indistinguishable (e.g., same‐sex friendship pairs) or distinguishable (e.g., heterosexual couples). For each possibility, what are the potential moderator effects (up to 8), how they might be estimated and tested, and how they can be interpreted are discussed. Submodels are also presented, based on patterns of moderation of the actor and partner effects, which are statistically simpler, more conceptually meaningful, and more powerful in testing moderator effects. Example analyses illustrate the recommended steps involved in an APIM moderation analysis.
We extend the actor-partner interdependence model (APIM), a model originally proposed for the analysis of dyadic data, to the study of groups. We call this extended model the group actor-partner interdependence model or GAPIM. For individual outcomes (e.g., satisfaction with the group), we propose a group composition model with four effects; for group-level outcomes (e.g., group productivity), we propose a model with two effects; and for dyad-level outcomes (e.g., liking of each of the other members of the group), a model with seven effects. For instance, for an individual outcome with gender as the group composition variable the effects are gender of the actor, gender of the other group members, actor similarity in gender to the others in the group, and the others' similarity in gender. For each of these models, we discuss the ways in which different submodels map onto social-psychological processes. We illustrate the GAPIM with two data sets.
A new method for assessing group synchrony is introduced as being potentially useful for objectively determining degree of group cohesiveness or entitativity. The cluster-phase method of Frank and Richardson (2010) was used to analyze movement data from the rocking chair movements of six-member groups who rocked their chairs while seated in a circle facing the center. In some trials group members had no information about others' movements (their eyes were shut) or they had their eyes open and gazed at a marker in the center of the group. As predicted, the group level synchrony measure was able to distinguish between situations where synchrony would have been possible and situations where it would be impossible. Moreover, other aspects of the analysis illustrated how the cluster phase measures can be used to determine the type of patterning of group synchrony, and, when integrated with multi-level modeling, can be used to examine individual-level differences in synchrony and dyadic level synchrony as well.
Research on in-group identification typically focuses on differences in individuals' identification at the individual level of analysis. We take a multilevel approach, examining the emergence of group influence on identification in newly formed groups. In three studies, multilevel confirmatory factor analysis confirmed two dimensions of identification-self-definition and self-investment (Leach et al., 2008)-at both the individual and the group level. As expected, the group had greater influence on individuals' identification the more group members interacted with each other. This was shown in experiments with varying amounts of real interaction (Study 1), in a longitudinal study of student project groups (Study 2), and in a longitudinal study that experimentally mimicked the development of online communities (Study 3). Together, these studies support a developmental model of identification at the group level that has implications for the understanding of social identity and small-group dynamics.
Members enter groups with different characteristics, for example, gender and ethnicity, and the Group Actor-Partner Interdependence Model (GAPIM) systematically tests several different effects of group composition for a given characteristic. By finding submodels of these effects, the GAPIM allows for empirically testing many theoretically meaningful models of differences within groups. Among the models that can be tested are models of diversity, relational demography, group norms, and contrast. This paper describes the four different steps of a GAPIM analysis and illustrates its application with two datasets. The first is an experimental dataset where gender composition is manipulated by presenting individuals with pictures of group members with whom they presumably would interact. The second dataset is a national sample of churchgoers who are members of different congregations, in which the effects of both a categorical and a continuous composition variable on a member-level outcome are assessed. SPSS and R syntax used for running the GAPIM is provided for each of these examples.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.