Two-Step Estimation of Incomplete Information Social Interaction Models With Sample Selection

ABSTRACT This article considers linear social interaction models under incomplete information that allow for missing outcome data due to sample selection. For model estimation, assuming that each individual forms his/her belief about the other members’ outcomes based on rational expectations, we propose a two-step series nonlinear least squares estimator. Both the consistency and asymptotic normality of the estimator are established. As an empirical illustration, we apply the proposed model and method to National Longitudinal Study of Adolescent Health (Add Health) data to examine the impacts of friendship interactions on adolescents’ academic achievements. We provide empirical evidence that the interaction effects are important determinants of grade point average and that controlling for sample selection bias has certain impacts on the estimation results. Supplementary materials for this article are available online.

[1]  Identification of Social Interactions , 2011 .

[2]  D. Pollard,et al.  Cube Root Asymptotics , 1990 .

[3]  Peer effects on substance use among American teenagers , 2004 .

[4]  S. Raphael,et al.  School-Based Peer Effects and Juvenile Behavior , 1997, Review of Economics and Statistics.

[5]  H. James.  VARIETIES OF SELECTION BIAS , 1990 .

[6]  B. Fortin,et al.  Some Challenges in the Empirics of the Effects of Networks , 2015, SSRN Electronic Journal.

[7]  Andres Aradillas-Lopez,et al.  Semiparametric estimation of a simultaneous game with incomplete information , 2010 .

[8]  W. Newey,et al.  Convergence rates and asymptotic normality for series estimators , 1997 .

[9]  Xiaodong Liu,et al.  Specification and Estimation of Social Interaction Models with Network Structures , 2010 .

[10]  Daiji Kawaguchi,et al.  Peer effects on substance use among American teenagers , 2002 .

[11]  Lung-fei Lee,et al.  Binary Choice Models with Social Network under Heterogeneous Rational Expectations , 2014, Review of Economics and Statistics.

[12]  Yves Zenou,et al.  Multivariate Choice and Identification of Social Interactions , 2012 .

[13]  R. Spady,et al.  AN EFFICIENT SEMIPARAMETRIC ESTIMATOR FOR BINARY RESPONSE MODELS , 1993 .

[14]  Georg Dürnecker,et al.  On the Allocation of Time , 2014 .

[15]  C. Manski.  MAXIMUM SCORE ESTIMATION OF THE STOCHASTIC UTILITY MODEL OF CHOICE , 1975 .

[16]  Lung-fei Lee,et al.  GMM estimation of social interaction models with centrality , 2010 .

[17]  Donald W. K. Andrews,et al.  Semiparametric Estimation of the Intercept of a Sample Selection Model , 1998 .

[18]  Aaron J. Sojourner.  Identification of Peer Effects with Missing Peer Data: Evidence from Project Star , 2013, SSRN Electronic Journal.

[19]  Yuanyuan Wan,et al.  Semiparametric identification of binary decision games of incomplete information with correlated private signals , 2014 .

[20]  Xiaohong Chen.  Chapter 76 Large Sample Sieve Estimation of Semi-Nonparametric Models , 2007 .

[21]  Lung-fei Lee,et al.  Estimation of Spatial Autoregressive Models with Randomly Missing Data in the Dependent Variable , 2013 .

[22]  John M. Rose,et al.  Binary choice models , 2015 .

[23]  Haiqing Xu.  Estimation of Discrete Games with Correlated Types , 2014 .

[24]  Adrian Pagan,et al.  Estimation, Inference and Specification Analysis. , 1996 .

[25]  Lung-fei Lee,et al.  A Social Interactions Model with Endogenous Friendship Formation and , 2016 .

[26]  Peter Arcidiacono,et al.  Estimating spillovers using panel data, with an application to the classroom , 2012 .

[27]  Xiaodong Liu,et al.  Identification and Efficient Estimation of Simultaneous Equations Network Models , 2014 .

[28]  Eleonora Patacchini,et al.  The Allocation of Time in Sleep: A Social Network Model with Sampled Data , 2013 .

[29]  Chao Yang,et al.  Social interactions under incomplete information with heterogeneous expectations , 2017 .

[30]  Shakeeb Khan,et al.  Irregular Identification, Support Conditions, and Inverse Weight Estimation , 2010 .

[31]  Bernard Fortin,et al.  Identification of Peer Effects through Social Networks , 2007, SSRN Electronic Journal.

[32]  J. Pepper.  How Do Response Problems Affect Survey Measurement of Trends in Drug Use , 2001 .

[33]  G. Imbens,et al.  Social Networks and the Identification of Peer Effects , 2013 .

[34]  J. Heckman.  Sample selection bias as a specification error , 1979 .

[35]  Anton I Badev,et al.  Discrete Games in Endogenous Networks: Theory and Policy , 2014 .

[36]  C. Manski.  Identification of Endogenous Social Effects: The Reflection Problem , 1993 .

[37]  William A. Brock,et al.  Discrete Choice with Social Interactions , 2001 .

[38]  H. Ichimura,et al.  SEMIPARAMETRIC LEAST SQUARES (SLS) AND WEIGHTED SLS ESTIMATION OF SINGLE-INDEX MODELS , 1993 .

[39]  Eleonora Patacchini,et al.  Endogenous Network Production Functions with Selectivity , 2016 .

[40]  P. Grieco.  Discrete Games with Flexible Information Structures: An Application to Local Grocery Markets , 2011 .

[41]  J. Powell,et al.  Semiparametric estimation of censored selection models with a nonparametric selection mechanism , 1993 .

[42]  Whitney K. Newey,et al.  Two-Step Series Estimation of Sample Selection Models , 2009 .

[43]  Xi Qu,et al.  Tobit models with social interactions: Complete vs incomplete information , 2018, Regional Science and Urban Economics.

[44]  Xu Lin,et al.  Identifying Peer Effects in Student Academic Achievement by Spatial Autoregressive Models with Group Unobservables , 2010, Journal of Labor Economics.

[45]  Lung-fei Lee,et al.  Identification and estimation of econometric models with group interactions, contextual factors and fixed effects , 2007 .

[46]  Steven N. Durlauf,et al.  Identification of binary choice models with social interactions , 2007 .