In this article I provide a (selective) review of the recent econometric literature on networks. I start with a discussion of developments in the econometrics of group interactions. I subsequently provide a description of statistical and econometric models for network formation and approaches for the joint determination of networks and interactions mediated through those networks. Finally, I give a very brief discussion of measurement issues in both outcomes and networks. My focus is on identification and computational issues, but estimation aspects are also discussed.

INTRODUCTION

Networks are “vulgar.” By that I mean: they are commonplace, ordinary. Although markets are the usual forum where economic phenomena take place, many social and economic behaviors are not mediated by prices. A great many studies have investigated the existence and quantification of spillover effects in education (e.g., Sacerdote, 2010), in the labor market (e.g., Topa, 2001) and, more recently, on non-cognitive outcomes (e.g., Neidell and Waldfogel, 2010 and Lavy and Sand, 2015). Many other behaviors are mediated through prices, but in such a way that it matters how agents are in contact with each other. Production and financial networks are natural examples (e.g., Atalay, Hortacsu, Roberts, and Syverson, 2011 for the first and Denbee, Julliard, Li, and Yuan, 2014 or Bonaldi, Hortacsu, and Kastl, 2014 for the second). The main conduit in these examples is the intervening role of “connections”: who is in direct or indirect contact with whom. This structure defines (and is possibly defined by) how information, prices and quantities reverberate in a particular social or economic system. This recognition has sparked a growing literature on various aspects of networks and their role in explaining various social and economic phenomena among economic theorists, empirical researchers and, more recently, econometricians.

This article aims at providing a (selective) overview of some recent advances and outstanding challenges in the applied econometric literature on this topic. I focus on both the role of networks in aiding the measurement of outcomes determined on an underlying network structure and on the formation of such structures. I also provide a brief discussion on measurement issues related to both tasks. Given constraints in space and expertise, this article is not exhaustive.