This paper extends Brock and Durlauf's (2001a, 2001b) binary choice complete network (or group interaction) model with homogeneous rational expectations to a general network model with heterogeneous rational expectations. In our model, individuals will form expectations regarding peers'...

Researchers using directed network data to estimate peer effects must somehow handle unreciprocated nominations. To better understand how peer effects operate and how best to estimate their effects, this paper investigates how the reciprocation of friendship mediates peer effects. We begin by...

In the presence of heteroskedastic disturbances, the MLE for the SAR models without taking into account the heteroskedasticity is generally inconsistent. The 2SLS estimates can have large variances and biases for cases where regressors do not have strong effects. In contrast, GMM estimators...

Disentangling peer effects from other confounding effects is difficult,and separately identifying endogenous and contextual effects is impossible for the linear-in-means model. This study confronts these problems by using spatial autoregressive models with group fixed effects. The nonlinearity...

This paper investigates how network attributes affect the strength of peer influences in adolescents' academic achievement and smoking behaviors. The results indicate that for both GPA and smoking, endogenous peer effects are stronger for network groups with larger size, higher network density...

This paper studies peer influences in adolescents' deviant behaviors, including drinking alcohol, doing dangerous things, skipping school and physical fighting, by a binary choice network model with heterogenous rational expectations proposed in Lee et al. (in press). For a wide range of...

This paper considers the specification and estimation of social interaction models with network structures and the presence of endogenous, contextual and correlated effects. With macro group settings, group-specific fixed effects are also incorporated in the model. The network structure provides...

Testing the proportionality of two large-dimensional covariance matrices is studied. Based on modern random matrix theory, a pseudo-likelihood ratio statistic is proposed and its asymptotic normality is proved as the dimension and sample sizes tend to infinity proportionally.