Identification of Social Interactions

Abstract

While interest in social determinants of individual behavior has led to a rich theoretical literature and many efforts to measure these influences, a mature "social econometrics" has yet to emerge. This chapter provides a critical overview of the identification of social interactions. We consider linear and discrete choice models as well as social networks structures. We also consider experimental and quasi-experimental methods. In addition to describing the state of the identification literature, we indicate areas where additional research is especially needed and suggest some directions that appear to be especially promising. KeywordsSocial interactions, social networks, identification JEL Classification C21, C23, C31, C35, C72, Z13 CommentsPrepared for the Handbook of Social Economics, J. Benhabib, A. Bisin, and M. Jackson, eds. We thank Andres Aradillas-Lopez, Jane Cooley, James Heckman, Charles Manski and Salvador Navarro for many conversations on the subject of this chapter. Financial support has been supplied to Blume by NSF grant CCF-0910940 and WWTF Grant "Die Evolution von Normen and Konventionen in der

With a little help from my friends? Quality of social networks, job finding and job match quality

“…This time-sequencing argument is similar to the one used by Cingano and Rosolia (2012) and Schmutte (2015). Second, as shown by Blume et al (2011), the non-linearity in models of limited dependent variables -like the one of equation (1) -may also break the reflection problem.…”

“…A large literature has developed in recent years focusing on the identification of social interactions (see e.g. Manski, 1993, Moffitt, 2001, and the comprehensive review by Blume et al, 2011). There are two features in our empirical setting which help dealing with the simultaneity problem.…”

Effect of Income on Trust: Evidence from the 2009 Crisis in Russia

“…5 See Durlauf (2002), Durlauf and Fafchamps (2005), and Blume et al (2010) on the methodological challenges in the econometric research on social capital.…”

Social Interaction Effects and Connection to Electricity: Experimental Evidence from Rural Ethiopia

“…For instance, the social influence of a friend may be larger than that of a stranger; similarly, it may be easier to derive information from observing a neighbor's behavior than from observing the behavior of someone farther away geographically. This idea is also discussed in Brock and Durlauf (2001), who distinguish between global interactions, in which the same weight is given to all population members, and local interactions, in which individuals within one's geographic or social vicinity are given greater weight (see also Moffitt, 2001). In a somewhat related vein, Akerlof (1997) uses a gravity model to describe how individuals may trade-that is, in a social interaction perspective-more with individuals who are 'close by' with respect to their lifestyle.…”

“…Since group behavior is simultaneously influenced by individual behavior, simple linear-in-means models, whereby an individual's action is regressed on the prevalence of this action within the group, cannot distinguish between exogenous and endogenous social interaction effects. Non-experimental solutions have been proposed, including the addition of further exclusion restrictions to the model and the reliance on nonlinearities, which allow for multiple equilibriums (for example, Brock and Durlauf, 2001;Blume and Durlauf, 2005). Other potential solutions rely on models in which one's behavior varies with lagged group outcomes under the assumption that "nonsocial forces act contemporaneously but social forces act on the individual with a lag" (Manski, 1993, p540).…”