Bilinear Mixed Effects Models For Relations Between Universities

TL;DR

This paper introduces bilinear mixed effects models to analyze dyadic data, capturing complex dependencies like transitivity and clustering, demonstrated through university relations in Iran from 1991-2005.

Contribution

It presents a novel application of bilinear mixed effects models to dyadic data, accounting for higher-order dependencies in international relations.

Findings

Detected significant second and third-order dependencies in university relations.

Demonstrated the model's effectiveness in capturing complex relational structures.

Provided insights into the dynamics of academic relations over time.

Abstract

this article illustrates the use of linear and bilinear random effects models to represent statistical dependencies that often characterize dyadic data such as international relations. In particular, we show how to estimate models for dyadic data that simultaneously take into account: regressor variables and third-order dependencies, such as transitivity, clustering, and balance. We apply this new approach to the relations among ph.d. of university in Iran over the period from 1991-2005, illustrating the presence and strength of second and third-order statistical dependencies in these data.