New Regression Models with Egocentric Social Network Data

Abstract

This paper introduces some regression models for a categorical dependent variable with data from egocentric social networks as covariates to analyze the determinants of the outcome for the subject and the determinants of the extent of agreement in the outcome between the subject and the people socially connected to the subject. The merits of the models introduced in this paper are their wide applicability to surveys that collect data on egocentric social networks and their ability to identify the determinants of agreement between subjects’ and their friends’ attitudinal or behavioral outcomes, controlling for the tendency to agree because of homophily in the choice of friends. An illustrative application from the Japanese General Social Survey data shows that several substantively distinct characteristics of egocentric networks affect subjects’ political party preferences and the extent of agreement between the political party preferences of subjects and their significant others.