Identification of Social Interactions through Partially Overlapping Peer Groups

American Economic Journal Applied Economics (Impact Factor: 2.76). 04/2010; 2(2):241-75. DOI: 10.1257/app.2.2.241
Source: RePEc

ABSTRACT In this paper, we demonstrate that, in a context where peer groups do not overlap fully, it is possible to identify all the relevant parameters of the standard linear-in-means model of social interactions. We apply this novel identification structure to study peer effects in the choice of college major. Results show that one is more likely to choose a major when many of her peers make the same choice. We also show that peers can divert students from majors in which they have a relative ability advantage, with adverse consequences on academic performance, entry wages, and job satisfaction. (JEL I23, J24, J31, Z13)

Download full-text


Available from: Michele Pellizzari, Aug 12, 2015
  • Source
    • "To tackle this last issue, we instrument the older sibling's test scores at age 16 using the average test scores of her school mates. 5 This peer identification strategy is similar to that adopted by Lee (2003), Bramoullé et al. (2009) and De Giorgi et al. (2010) and is based on the presence of some intransitivity in the network of peers. Intransitivity occurs if a person interacts with her peers but not with all of the peers of her peers. "
    [Show abstract] [Hide abstract]
    ABSTRACT: We provide the first empirical evidence on direct sibling spillover effects in school achievement using English administrative data. Our identification strategy exploits the variation in school test scores across three subjects observed at age 11 and 16 and the variation in the composition of school mates between siblings. These two sources of variation have been separately used to identify school peer effects, but never in combination. By combining them we are able to identify a sibling spillover effect that is net of unobserved child, family and school characteristics shared by siblings. We find a modest spillover effect from the older sibling to the younger but not vice versa. This effect is considerably higher for siblings from deprived backgrounds, where sibling sharing of school knowledge might compensate for the lack of parental information.
  • Source
    • "This identification strategy is related to the formal treatment that can be found in Laschever (2009) and De Giorgi et al. (2010). The validity and performance of this instrument is further discussed in Section 5. "
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper seeks to understand the role that peer comparisons play in the determination of executive compensation. I exploit a recent change in the Securities and Exchange Commission’s regulations that requires firms to disclose the peer companies used for determining the compensation of their top executives. Using a new dataset of S&P 900 companies’ choice of benchmarking firms during two fiscal periods (2007 and 2008), I investigate what determines the choice of comparison firms. I find that companies have a preference for choosing larger and higher-CEO-compensation firms as their benchmark. Though I find that companies prefer to choose as their benchmark peers with similar firm characteristics, for CEO compensation, this effect is countered by a preference for firms with higher-than-own CEO compensation. Using the complete map of firms’ choices, I implement an instrumental variable strategy that uses the characteristics of peers-of-peers to estimate the effect of others’ compensation on own compensation. For Fiscal Year 2007, I find an elasticity of 0.5.
    Journal of Economic Behavior & Organization 09/2013; 93. DOI:10.1016/j.jebo.2013.07.002 · 1.01 Impact Factor
  • Source
    • "Cooley identifies peer spillovers by comparing classrooms with varying percentages of students that are held accountable to classrooms of similar composition where students were not held accountable. A novel strategy for disentangling endogenous from exogenous effects involves using partially overlapping reference groups (Lin, 2010; Calvó- Armengol et al., 2009; De Giorgi et al., 2010; Laschever, 2009). I describe this strategy in depth in Section 3. "
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper provides evidence on peer effects in educational achievement exploiting for the first time a unique data set on social networks within primary schools in Uruguay. The relevance of peer effects in education is still largely debated due to the identification challenges that the study of social interactions poses. I adopt a recently developed identification method that exploits detailed information on social networks, i.e. individual-specific peer groups. This method enables me to disentangle endogenous effects from contextual effects via instrumental variables that emerge naturally from the network structure. Correlated effects are controlled, to some extent, by classroom fixed effects. I find significant endogenous effects in standardized tests for reading and math. A one standard deviation increase in peers’ test score increases the individual’s test score by 40% of a standard deviation. This magnitude is comparable to the effect of having a mother that completed college. By means of a simulation I illustrate that when schools are stratified by socioeconomic status peer effects may operate as amplifiers of educational inequalities.
Show more