EcoSta 2018: Registration
View Submission - EcoSta2018
A0639
Title: Estimation and classification for varying-coefficient panel data model with latent structures Authors:  Tao Huang - Shanghai University of Finance and Economics (China) [presenting]
Abstract: A varying coefficient panel data model with unknown group structures is considered, where the group membership of each individual and the number of groups are left unspecified. We first develop a triple localization approach to estimate the unknown coefficient functions, and then identify latent grouped structures via community detection method. To improve the efficiency of the resultant estimator, we further propose a two-stage estimation method that enables the resulting estimator achieve optimal rates of convergence. In the theoretical part, the asymptotic theory of the resultant estimators are derived. In particular, we provide the convergence rates and the asymptotic distribution of our estimators. In the empirical part, several simulated examples and a real data analysis are presented to illustrate the finite sample performance of the proposed methods.