Gistelinck, F., & Loeys, T.
Multilevel autoregressive models for longitudinal dyadic data
In social and behavioral science, dyadic research has become more and more popular. In case of cross-sectional dyadic data, one can apply the actor-partner interdependence model (APIM). When dyads are measured repeatedly over time, applied researchers are often hesitant to analyze such data due to the statistical complexity. In this paper, we introduce a user-friendly Shiny-application, called the LDDinSEM-application. The app automatically fits the lagged dependent actor-partner interdependence model (LD-APIM), a multilevel autoregressive model extension of the APIM within the structural equation modeling (SEM) framework. The application allows the researcher to investigate the effects of an antecedent on an outcome, given the previous outcome. We illustrate the app using an empirical example assessing the actor and partner effects of positive relationship feelings on next day’s intimacy in heterosexual couples.
Testing, Psychometrics, Methodology in Applied Psychology, 2020, Vol. 27, pp. 433-452, DOI: 10.4473/TPM27.3.7
