A new round robin analysis of variance for social interaction data.

Experimental social psychology has dealt primarily with situations that are not true social interactions; in a typical study, a subject responds to a fixed, artificial social stimulus such as a photograph, written description, or performance by a confederate. Although these artificial social stimuli provide experimental control over independent variables and can be analyzed using the types of statistical models originally developed for nonsocial experimental research, they provide little or no information about the interactive aspects of social behavior—the reciprocity or mutual contingency of the behavior of interaction partners. This paper describes a nonexperimental design specifically tailored to social interaction data that provides more information about individual differences and social influence in social interactions: a round robin design in which each person interacts with every other person. After a brief review of available models, a new and more general model for the analysis of social interaction data is presented, with an empirical demonstration using vocal activity data. Experimental social psychology has often been limited to the study of artificial, one-sided social situations in which the subject responds to some fixed social stimulus created by the experimenter; this has been the case even in research on person perception and interpersonal attraction, where it is especially apparent that the behaviors and attitudes of persons are mutually contingent (i.e., As liking for B affects Bs liking for A, and vice versa). In research on subject reactions to fixed stimuli (rather than the reactions to other persons in the context of naturally occurring social interactions), information about the reciprocity of social behaviors is lost. Moreover, the use of standardized, artificial stimuli often precludes having stimuli that are representative of typical interactions. Thus,