Panel data are often characterized by cross-sectional heterogeneity, and a exible yet parsimonious way of modeling heterogeneity is to cluster units into groups. A group pattern of heterogeneity may exist not only in the mean but also in the other characteristics of the distribution. To identify latent groups and recover the heterogeneous distribution, we propose a clustering method based on composite quantile regressions. We show that combining the strength across multiple panel quantile regression models improves the precision of the group membership estimates if the group structure is common across quantiles. Asymptotic theories for the proposed estimators are established, while their finite-sample performance is demonstrated by simulations. We finally apply the proposed methods to analyze the cross-country output effect of infrastructure capital.
Dr. Xuan Leng is an assistant professor at Wang Yanan Institute for Studies in Economics(WISE), School of Economics (SOE) and the Gregory and Paula Chow Center for Economic Research, Xiamen University. Before, she was a postdoc at the Econometric Institute of the Erasmus University Rotterdam and the department of Statistics & Applied Probability of National University of Singapore. She obtained the PhD in statistics at the University of Science and Technology of China, under the supervision of Prof. Taizhong Hu and Prof. Liang Peng (visiting PhD 2014-2016 in U.S.). Her research interests include panel data analysis and extreme value theory in risk management.