The assessment of mediation in dyadic data is an important issue if researchers are to test process models. Using an extended version of the actor-partner interdependence model the estimation and testing of mediation is complex, especially when dyad members are distinguishable (e.g., heterosexual couples). We show how the complexity of the model can be reduced by assuming specific dyadic patterns. Using structural equation modeling, we demonstrate how specific mediating effects and contrasts among effects can be tested by phantom models that permit point and bootstrap interval estimates. We illustrate the assessment of mediation and the strategies to simplify the model using data from heterosexual couples.Models of mediation are common and of great importance, as they can provide information about causal relationships between variables that are mediated by one or more sets of intervening variables. Mediation refers to a mechanism through which an initial .X/ influences an outcome .Y / by a third variable .M /, termed mediator or intervening variable (Baron & Kenny, 1986;Judd & Kenny, 1981). In this mediation model, the effect from X to M is commonly designated as a, the effect from M on Y as b, and the effect from X on Y as c 0 (MacKinnon, 2008). The mediating or indirect effect (IE) of X on Y equals ab and the total effect equals ab C c 0 .Over the last decade, researchers have begun to examine mediating mechanisms in dyadic data. The most commonly used model for this purpose is the actor-partner interdependence Correspondence should be addressed to Thomas Ledermann,

Family researchers have used the actor-partner interdependence model (APIM) to study romantic couples, parent-child dyads, and siblings. We discuss a new method to detect, measure, and test different theoretically important patterns in the APIM: equal actor and partner effect (couple pattern); same size, but different signs of actor and partner effects (contrast pattern); and zero partner effects (actor-only pattern). To measure these different patterns, as well as others, we propose the estimation of the parameter k, which equals the partner effect divided by the actor effect. For both indistinguishable dyad members (e.g., twins) and distinguishable dyad members (e.g., heterosexual couples), we propose strategies for estimating and testing different models. We illustrate our new approach with four data sets.

Using data from 198 couples, this study examines whether associations between stress occurring outside of the dyad and key indicators of relationship functioning are mediated by stress arising within the dyad. Findings suggest that relationship satisfaction and sexual activity are governed by hassles and problems experienced within the dyad that are in turn related to stress arising outside the dyad. Associations between external stress and relationship functioning are stronger for daily hassles than for critical life events. Higher levels of daily stress predicted less sexual activity for maritally dissatisfied women and more sexual activity for maritally dissatisfied men. Self-reports of stress covaried with self-reported indexes of satisfaction and sexuality, suggesting that contextual influences are broadly influential in intimate relationships.

Studying dyads, very often there is a theoretical construct that has an effect on both members, such as relationship harmony or shared environment. To model such influences, the common fate model (CFM) is often the most appropriate approach. In this article, we address conceptual and statistical issues in the use of the standard CFM and present a series of variations, all of which are estimated by structural equation modeling (SEM). For indistinguishable dyad members (e.g., gay couples), we describe the use of a multilevel SEM method. Throughout the paper, we draw connections to the actor-partner interdependence model (APIM). We also discuss the analysis of hybrid models that combines both the CFM and the APIM. The models are illustrated using data from heterosexual couples.