学术报告新

Shuyang Sheng is an Associate Professor in the School of Management and Economics at the Chinese University of Hong Kong, Shenzhen. She holds a Ph.D. in Economics from the University of Southern California. Prior to joining CUHK-Shenzhen, she was an Assistant Professor in the Department of Economics at the University of California at Los Angeles. Her primary research areas are econometrics and labor economics. She specializes in developing econometric methods for network formation models and social interaction models. Her work has been published in Econometrica and Journal of Labor Economics.

This paper explores the identification and estimation of social interaction models with endogenous groups. We characterize group selection using a two-sided many-to-one matching model, where individuals choose groups based on their preferences, while groups rank and admit individuals based on qualification criteria until reaching capacity limits. The group selection leads to bias in standard estimates of peer effects, which is challenging to correct for due to equilibrium effects. To simplify this selection bias, we use the limiting approximation of a market as its size grows. Assuming exchangeable unobservables, we can express an individual's selection bias as a group-invariant nonparametric function of their preference and qualification indices. We propose a sieve OLS estimator for peer effects that is \sqrt{n}-consistent and asymptotically normal. Applying our approach to analyze peer effects in Chilean high schools, we find that ignoring selection bias results in an overestimation of peer effects and the misclassification of self-selection as school effectiveness. Our findings emphasize the empirical importance of selection bias and its policy implications.