University of Connecticut IARR – Crete Modeling Nonindependence: The Actor-Partner Interdependence Model 3/27/2017 David A. Kenny University of Connecticut http://davidakenny.net/dyad.htm IARR 2006
Overview Model Three Brief Examples Estimation Multilevel Modeling (SPSS) Structural Equation Modeling (AMOS)
Between
Within
Mixed
Mixed Independent Variable Definition X does not equal X’ for all pairs Or X + X’ equal the same value for every pair Allows for the estimation of partner effects
Types of Dyads Definitions Distinguishable Dyads with a categorical within-dyads variables that makes a difference E. g., parent-child Indistinguishable Ordering of the two members is arbitrary E.g. roommates Whether dyads are distinguishable or not is matter of theoretical and statistical considerations.
Actor-Partner Interdependence Model X Y partner partner actor X' Y'
Types of APIM Models actor only a > 0; p = 0 partner only couple model a = p social comparison model a + p = 0
Example 1: Kraemer-Jacklin Study Children in dyads are observed playing Variables X – Gender X’ – Partner Gender XX’ – Same vs. Opposite Gender Y – Share toys with partner
APIM Effects Actor: Do girls share more than boys? Yes, but the effect is small. Partner: Do children share more when their partner is a girl? Yes and the effect is twice as large as the actor effect. Actor-Partner Interaction: Is there more sharing with same-gendered partners? Not much of a difference.
Example 2: Personality and Perceived of Control (Cook) Siblings: one college student and one adolescent Variables Relative age (within dyads) Assertiveness (mixed) Cooperativeness (mixed) Perceived Control (outcome variable)
Example 2: Results Gender: no effects Relative age older seen as more powerful Assertiveness positive actor effect negative partner effect Cooperativeness no actor effect positive partner effect
Example 3: Perception of Romantic Partners: Measures and Sample Both partners form a perception A’s perception -- P(A) Each guesses how his or her partner’s view A’s guess of how B views the issue -- P(AB) Probability Sample (Acitelli) 248 married couples 90 dating couples
Perception of Romantic Partners: Path Model bias P(A) P(AB) accuracy accuracy bias P(BA) P(B)
Perception of Romantic Partners: Conclusions Few Gender Differences Few Effects for Married vs. Dating Accuracy and Bias for Each Measure Strength of Effects Varies by Measure
Perception of Romantic Partners: Results
Dyadic Data Organization Individual One record for each individual Only that individual’s data on the record Dyad (useful for distinguishable dyads) Each record one dyad Different variables for each person Pairwise (useful for indistinguishable dyads) One record for each person The person’s data and partner data included (each data point included twice)
Estimation Indistinguishable members Multilevel Modeling Pairwise Data File Illustrate with SPSS Distinguishable members Structural Equation Modeling Dyad Data File Illustrate with AMOS