Kernel Estimation of a Quantile Partially Additive Linear Regression Model

• Activity Number: 305
• Type: Contributed
• Date/Time: Tuesday, August 6, 2013 : 8:30 AM to 10:20 AM
• Sponsor: Section on Nonparametric Statistics
• Author(s): Dawit Zerom*+
• Companies: California State University at Fullerton
• Keywords: Kernel smoother ; Oracle property ; Quantile regression ; Partially additive linear ; Time series

Abstract

We propose a kernel-based estimator for the finite-dimensional parameter of a partially additive linear quantile regression model. For dependent processes that are strictly stationary and absolutely regular, we establish a precise convergent rate and show that the estimator is root-n consistent and asymptotically normal. In addition to conducting a simulation experiment to evaluate the finite sample performance of the estimator, an application to U.S. inflation is presented. We use the real data example to motivate how partially additive linear quantile models can offer an alternative modeling option for time series data as well as help illustrate the proposed estimator.