The Social-Relations Model for Asymmetric-Block-Design Data: A Tutorial With R

We provide a guide to estimating social-relations-model (SRM) parameters for data collected with the asymmetric block design using R. SRM estimates reflect how people differ in the social behaviors they emit and elicit from others and the extent to which they behave differently with each unique partner. Such analyses have proven useful in studies of the power of leaders, negotiation effectiveness, and personality perception, to name a few. The SRM parameters can be estimated for data collected with various designs; the most common design is the round-robin. A less used design in SRM studies is the asymmetric block design, which involves measurements taken from dyadic interactions of individuals from two different social categories (e.g., speed-dating studies in which different-gendered participants interact). In this guide, we show how to estimate SRM parameters for asymmetric block design by specifying mixed-effect models with two R packages: glmmTMB and brms. Specifically, we show how to calculate SRM estimates for (a) one continuous outcome, (b) multiple measures of a continuous outcome, (c) bivariate correlations for two continuous outcomes, (d) one dichotomous outcome, (e) bivariate and multivariate associations between continuous SRM variables and one dichotomous outcome (in supplementary work-around), and (f) data from mother and child interactions rather than the more common speed-dating data. In all analyses, we illustrate how to model both fixed and random effects to allow testing additional fixed effects, such as group characteristics and the order of interaction between participants.