Predictors and outcomes of social network compositions: A compositional structural equation modeling approach

Abstract

Proportions of a total, including social network compositions (proportions of partner, family, friends, etc.) lie in a restricted space, which challenges statistical analysis. Network compositions can be both dependent and explanatory variables and are usually measured with error by survey instruments. Structural equation models make it possible to correct measurement error bias. Coenders et al. (2011) fitted a factor analysis model to transformed network compositions. In this article, we use another transformation called an isometric log-ratio and we extend the model to include predictors and outcomes. The findings and hypotheses in the literature can be reformulated with isometric log-ratios in a more interpretable manner. For instance, we find relationships of gender with partner support, of education and extraversion with friend support, and of family support with tie multiplexity and closeness.