Graphic methods for interpreting longitudinal dyadic patterns from repeated-measures actor–partner interdependence models.

Abstract

Researchers commonly use repeated-measures actor-partner interdependence models (RM-APIM) to understand how romantic partners change in relation to one another over time. However, traditional interpretations of the results of these models do not fully or correctly capture the dyadic temporal patterns estimated in RM-APIM. Interpretation of results from these models largely focuses on the meaning of single-parameter estimates in isolation from all the others. However, considering individual coefficients separately impedes the understanding of how these associations combine to produce an interdependent pattern that emerges over time. Additionally, positive within-person, or actor, effects are commonly misinterpreted as indicating growth from one time point to the next when they actually represent decline. We suggest that change-as-outcome RM-APIMs and vector field diagrams (VFDs) can be used to improve the understanding and presentation of dyadic patterns of association described by standard RM-APIMs. The current article briefly reviews the conceptual foundations of RM-APIMs, demonstrates how change-as-outcome RM-APIMs and VFDs can aid interpretation of standard RM-APIMs, and provides a tutorial in making VFDs using multilevel modeling. (PsycINFO Database Record

Physiological linkage and affective dynamics in dyadic interactions between adolescents and their mothers

“…For mothers, the actor RSA effect was statistically significant and positive. Because the value of this effect was positive but less than 1, this actor RSA effect reflects regression to the mean (e.g., Perry et al, ), in which epochs marked by high RSA tend to be followed by lower RSA epochs, while low RSA epochs tend to be followed by higher RSA epochs, centered around the individual's mean level of RSA. Maternal depressive symptoms moderated the actor RSA effect for mothers.…”

“…Broadly, high levels of RSA during one epoch predicted continued high levels of RSA in the subsequent epoch for both mothers and youth throughout the discussion tasks. The magnitude of the actor effects (positive, but less than 1) also indicates a “regression to the mean” effect (Perry et al, ), such that elevated RSA in one epoch predicted subsequent RSA that was elevated, but closer to the mean (while low RSA in one epoch predicted subsequent RSA levels that were low, but closer to the mean).…”

The Association between Symptom Accommodation and Emotional Coregulation in Couples with Binge Eating Disorder

“…Probing of this interaction revealed that at low levels of accommodation, there was a positive actor effect for the partner. Because this actor effect is closer to a value of 1.0, it indicates that partners’ arousal is more stable over time when accommodation was lower relative to when accommodation was higher (Perry et al., ).…”

Models for Dyadic Data. Chapter in Cambridge Handbook of Research Methods in Clinical Psychology

“…In the context of psychotherapy, this model is sometimes termed a repeated measures (RM) APIM (cf. Baucom, Dickenson, et al, 2015;Crowell et al, 2014;Perry et al, 2017). Extending the model to further include additional occasions allows testing whether the actor and partner effects can explain the longitudinal interrelations -i.e., whether the processes are interdependent over time (Laurenceau & Bolger, 2005).…”

“…But such a constraint can be relaxed in order to account for potential influences of lags greater than one or to test for differences in the parameters across various segments in the data. As noted previously, if an APIM is applied to more than two measures, and the actor and partner influences are constrained to be equal over time, the resulting RM-APIM is equivalent to the auto-regressive model described here (Nestler et al, 2015;Perry et al, 2017). AR models allow answering questions pertinent to dyadic interactions.…”