Estimation of Social-Influence-Dependent Peer Pressures in a Large Network Game

Abstract

Research on peer effects in sociology has been focused for long on social influence power to investigate the social foundations for social interactions. This paper extends Xu (forthcoming)’s large–network–based game model by allowing for social–influence–dependent peer effects. In a large network, we use the Katz–Bonacich centrality to measure individuals’ social influences. To solve the computational burden when the data come from the equilibrium of a large network, we extend Aguirregabiria and Mira (2007)’s nested pseudo likelihood estimation (NPLE) approach to our large network game model. Using the Add Health dataset, we investigate peer effects on conducting dangerous behaviors of high school students. Our results show that peer effects are statistically significant and positive. Moreover, a student benefits more (statistically significant at the 5% level) from her conformity, or equivalently, pays more for her disobedience, in terms of peer pressures, if friends have higher social-influence status.