【主讲】刘晓冬 助教授 (University of Colorado Boulder)
【主题】Identification and Efficient Estimation of Simultaneous Equations Network Models
【时间】2013年8月2日 (周五) 15：30-17：00
【地点】上海财经大学经济学院楼701室
【语言】英文
【摘要】We consider identification and estimation of social network models in a system of simultaneous equations. We show that, with or without row-normalization of the social adjacencymatrix, the network model has different equilibrium implications, needs different identificationconditions, and requires different estimation strategies. When the adjacency matrix is not row-normalized, different positions of the agents in a network captured by the Bonacich centralitycan be used to identify social interaction effects and improve estimation efficiency. We showthat the identification condition for the model with a non-row-normalized adjacency matrix isweaker than that for the model with a row-normalized adjacency matrix. We suggest 2SLS and3SLS estimators using instruments based on the Bonacich centrality of each network to improveestimation efficiency. The number of such instruments depends on the number of networks.When there are many networks in the data, the proposed estimators may have an asymptoticbias due to the presence of many instruments. We propose a bias-correction procedure for themany-instrument bias. Simulation experiments show that the bias-corrected estimators performwell infinite samples.
