Associate Professor Liu Yanbo’s Collaborative Paper Published Online in Top Econometrics Journal Journal of Econometrics
Recently, the collaborative paper Estimation and inference for causal functions with multi-way clustered data by Associate Professor Liu Yanbo from the School of Economics at Shandong University, Assistant Researcher Liu Nan from the School of Economics at Xiamen University and Professor Yuya Sasaki from the Department of Economics at Vanderbilt University, USA, was published online in Journal of Econometrics, an international top econometrics journal.
This paper proposes a method for estimating and consistent inference of various causal functions (such as conditional average treatment effect and continuous treatment effect) under multi-way clustered data structure. The core idea is to identify causal functions as Neyman orthogonal moment conditions dependent on high-dimensional nuisance parameters. This paper adopts a two-step estimation procedure: first, estimate high-dimensional nuisance parameters using non-parametric methods, and project the estimated Neyman orthogonal signal into the basis function space growing with the sample size. At the same time, two estimation methods, full-sample estimation and multi-way clustered cross-fitting, are studied, and the corresponding functional Gaussian approximation theory is established. In terms of inference, this paper proposes a multi-way clustered robust sieve estimation score bootstrap method. Simulation results show that this method has good performance in finite samples. This paper also applies the proposed estimation and inference methods to empirical analysis.
Liu Yanbo is an associate professor at the School of Economics at Shandong University. He obtained his Ph.D. in Economics from Singapore Management University. His research directions are non-parametric/semi-parametric econometrics, micro-econometrics, financial econometrics, etc. Research achievements have been accepted or published in international journals such as International Economic Review, Journal of Econometrics, Econometric Theory, and Economics Letters.
