Statistics Seminar（2018-13）

Topic: Nonparametric Estimation of Generalized Transformation Panel Data Models with Fixed Effects

Speaker: Xi Wang, Shanghai Lixin University of Accounting and Finance

Time: Thursday, September 20, 14:00-15:00

Place: Room 216, Guanghua Building 2

Abstract:

Transformation model is appealing to microeconomics practitioners. In particular, the generalized transformation models, where both the transformation function and the structural function are unspecified, are general to incorporate many common microeconometric models as special cases. This paper considers the nonparametric estimation of various generalized transformation panel data models with fixed effects. We begin with the model with an additive structure, where each regressors are separated additively by a sequence of nonlinear and unknown structural functions. A novel nonparametric estimator is developed for the structural functions. Our estimator has an advantage of explicit expression and easy computation. We additionally extend the model to a more general one where the relationship of regressors are non-separable and unknown, and propose a nonparametric estimator. All estimators are shown to be uniformly consistent and asymptotically normal. A series of Monte Carlo experiments are carried out to examine the finite sample properties of the nonparametric estimators. Finally, we apply the estimator to the health expenditure study using US survey data.

Introduction:

Xi Wang, Assistant Professor at Shanghai Lixin University of Accounting and Finance. She received her bachelor’s and master’s degree from Renmin University of China, and Ph.D. in Economics at HongKong University of Science and Technology, Wang's research interest is micro-econometrics. Her current portfolio is centered on semiparametric and nonparametric estimation of discrete choice models, transformation models, non-separable models, and related applied micro- econometric studies.

Your participation is warmly welcomed!