The actor–partner interdependence model for categorical dyadic data: A user‐friendly guide to GEE

Abstract

The actor–partner interdependence model (APIM) has been widely used for the analysis of pairs of individuals who interact with each other. The goal of this article is to detail in a nontechnical way how the APIM for binary or count outcomes can be implemented and how actor and partner effects can be estimated using generalized estimating equations (GEE) methodology. Both SPSS‐ and SAS‐syntax needed to estimate the model and the interpretation of the output are illustrated using data from a study exploring the effect of satisfaction with the relationship before the breakup on unwanted pursuit behavior after the breakup in formerly married partners. The use of this GEE method will allow researchers to test a wide array of research hypotheses.

Actor–Partner Effects of Male Couples Substance Use with Sex and Engagement in Condomless Anal Sex

“…Actor and partner effects were then estimated using Generalized Estimated Equations (GEE) algorithm described by Loeys et al [11] which accounts for the correlation between individuals within a couple by using a robust variance estimate. The Wald test based on robust variance of the GEE models performs quite well in testing actor and partner effects when the number of dyads is more than 50 dyads [12].…”

Ask and you might receive: The actor–partner interdependence model approach to estimating cultural and gender variations in social support

“…Marginal R 2 , which reveals the proportion of variance explained by the fitted model (Hardin & Hilbe, ), are presented in all APIM effect tables. All APIM related analyses were conducted using the “PROC GENMOD” command in SAS v9.3 following the procedures specified in the study of Loeys, Cook, De Smet, Wietzker, and Buysse ().…”

“…Results in Model 2 using gender as the moderator showed that there were no significant main effects. However, there was a significant three-way interaction for Friend's actor effect-higher supportive NRI perceived by the Friend was related to more emotionfocused support provided by female friends at a rate of 2 The exponentiated estimates (Rate Ratios) indicate the amount of change in the dependent variable for every unit increase in the independent variable, controlling for all other effects in the model (Loeys et al, 2014). 3 All partial correlations have accounted for both actor and partner effects.…”

Giving dyadic data analysis away: A user‐friendly app for actor–partner interdependence models

“…The latter approach may outperform the first, especially when the number of dyads is small. For a nontechnical introduction of the implementation of GEE in SPSS or R, we refer the interested reader to Loeys, Cook, De Smet, Wietzker, and Buysse (2014). The APIM with categorical outcomes can be fitted within the SEM framework (Josephy, Loeys, & Rosseel, 2016).…”