Indistinguishability tests in the actor–partner interdependence model

Abstract

When considering dyadic data, one of the questions is whether the roles of the two dyad members can be considered equal. This question may be answered empirically using indistinguishability tests in the actor-partner interdependence model. In this paper several issues related to such indistinguishability tests are discussed: the difference between maximum likelihood and restricted maximum likelihood based tests for equality in variance parameters; the choice between the structural equation modelling and multilevel modelling framework; and the use of sequential testing rather than one global test for a set of indistinguishability tests. Based on simulation studies, we provide guidelines for best practice. All different types of tests are illustrated with cross-sectional and longitudinal data, and corroborated with corresponding R code.

Couples Dealing With Pediatric Blood Cancer: A Study on the Role of Dyadic Coping

“…This means that the pattern of findings found in our male subsample was fully replicated within our female subsample and that for both parents of children with cancer, dyadic coping and relationship functioning are intertwined. However, the absence of evidence for a difference might also be due to the low power to detect such interactions in small samples (Gistelinck et al, 2018). For the individual outcomes, the patterns for men versus women were more heterogeneous, thus less parallels could be drawn between them.…”

Dyadic measurement invariance and its importance for replicability in romantic relationship science

“…In the context of research on heterosexual romantic couples, gender/sex (see van Anders, 2015 for the meaning of this term) is easily the most common distinguishing variable used, such that separate levels of X and Y variables, and separate actor, partner, and/or mutual influence effects (along with other parameters) are estimated for men and women. Although numerous strategies are available for statistically testing distinguishability of actor‐partner effects (Gistelinck et al, 2018; Olsen & Kenny, 2006), it is safe to say—at least in the context of dyadic studies on heterosexual romantic relationships—that the majority of researchers anticipate that men and women will somehow differ in terms of the variables of interest as well as the patterns of association between them, and default to modeling dyad partners as distinguishable without always testing this assumption directly (cf. Kenny et al, 2006).…”

“…By enabling researchers to appropriately account for the interdependence of observations within a dyad, analytic paradigms like the Actor‐Partner Interdependence Model (APIM; Cook & Kenny, 2005), the Common Fate Model (CFM; Ledermann & Kenny, 2012), the Mutual Influence Model (MIM; Kenny, 1996; Woody & Sadler, 2005), the Truth and Bias Model (TBM; West & Kenny, 2011), and dyadic response surface analyses (Schönbrodt, Humberg, & Nestler, 2018) have become mainstays of basic relationship science. It also seems as though every year there are new extensions to these models (Gistelinck, Loeys, Decuyper, & Dewitte, 2018; Ledermann, Macho, & Kenny, 2011; Loeys & Molenberghs, 2013) or entirely new models of dyadic processes (Ledermann & Macho, 2014; West & Kenny, 2011) made available, empowering researchers to ask and to answer new questions about romantic relationships. It is an exciting time to be a close relationships scholar.…”

Dyadic Measurement Invariance and Its Importance for Replicability in Romantic Relationship Research

“…In the context of research on heterosexual romantic couples, gender/sex (see van Anders, 2015 for the meaning of this term) is easily the most common distinguishing variable used, such that separate levels of X and Y, and separate actor and partner effects (along with other parameters) are estimated for men and women. Although numerous strategies are available for statistically testing distinguishability of actor-partner effects (Olsen & Kenny, 2006;Gistelinck, Loeys, Decuyper, & Dewitte, 2018), it is safe to say-at least in the context of dyadic studies on heterosexual romantic relationships-that the majority of researchers anticipate that men and women will somehow be different in terms of the variables of interest and the patterns of association between them, and without always testing this assumption directly, default to modeling dyad partners as distinguishable (cf. Kenny et al, 2006).…”

“…By enabling researchers to appropriately account for the interdependence of observations within a dyad, analytic paradigms like the Actor-Partner Interdependence Model (APIM; Cook & Kenny, 2005) and the Common Fate Model (CFM; Ledermann & Kenny, 2012) have become mainstays of basic relationship science. It also seems as though every year there are new extensions to these models (e.g., Gistelinck, Loeys, Decuyper, & Dewitte, 2018;Ledermann, Macho, & Kenny, 2011;Loeys & Molenberghs, 2013) or entirely new models of dyadic processes (e.g., Ledermann & Macho, 2014;West & Kenny, 2011) made available, empowering researchers to ask and to answer new questions about romantic relationships. It is an exciting time to be a close relationships scholar.…”