Title: Clustering large scale generalized linear longitudinal models with grouped patterns of unobserved heterogeneity
Authors: Tomohiro Ando - Melbourne Business School (Australia) [presenting]
Jushan Bai - Columbia University (United States)
Abstract: Methods are provided to flexibly capture the unobservable heterogeneity from longitudinal data in the context of the exponential family of distributions. The group membership of individual units is left unspecified, and their heterogeneity is influenced by group-specific unobservables as well as the heterogeneous regression coefficients. We discuss a computationally efficient estimation method and derive asymptotic theory. The established asymptotic theory includes a uniform consistency of the estimated group membership. To test the heterogeneous regression coefficients within-group or not, we propose the Swamy-type test that takes account unobserved heterogeneity. We apply the proposed method to study the market structure of the taxi industry in New York City.