A dynamic social relations model for clustered longitudinal dyadic data with continuous or ordinal responses

Rebecca Pillinger; Fiona Steele; George Leckie; Jennifer Jenkins

doi:10.1093/jrsssa/qnad115

A dynamic social relations model for clustered longitudinal dyadic data with continuous or ordinal responses

J R Stat Soc Ser A Stat Soc. 2023 Sep 5;187(2):338-357. doi: 10.1093/jrsssa/qnad115. eCollection 2024 Apr.

Authors

Rebecca Pillinger¹, Fiona Steele², George Leckie³, Jennifer Jenkins⁴

Affiliations

¹ Independent Researcher, Edinburgh, UK.
² Department of Statistics, London School of Economics & Political Science, London, UK.
³ School of Education, University of Bristol, Bristol, UK.
⁴ Applied Psychology and Human Development, University of Toronto, Toronto, Canada.

Abstract

Social relations models allow the identification of cluster, actor, partner, and relationship effects when analysing clustered dyadic data on interactions between individuals or other units of analysis. We propose an extension of this model which handles longitudinal data and incorporates dynamic structure, where the response may be continuous, binary, or ordinal. This allows the disentangling of the relationship effects from temporal fluctuation and measurement error and the investigation of whether individuals respond to their partner's behaviour at the previous observation. We motivate and illustrate the model with an application to Canadian data on pairs of individuals within families observed working together on a conflict discussion task.

Keywords: autoregressive model; cross-lagged effects; dyadic data; dynamic panel model; round-robin data.