Nonparametric Quantile Estimations for Dynamic Smooth Coefficient Models

• 成果类型: Article
• 署名作者: Cai, Zongwu; Xu, Xiaoping
• 署名单位: University of North Carolina; University of North Carolina Charlotte; Xiamen University; China University of Geosciences
• 刊物名称: JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION
• ISSN/ISSBN: 0162-1459
• DOI: 10.1198/016214508000000977
• 发表日期: 2008
• 页码: 1595-1608
• 关键词: nonlinear time-series; REGRESSION QUANTILES; growth charts; conditional quantile; linear-models; inference; splines; selection

摘要

We suggest quantile regression methods for a class of smooth coefficient time series models. We use both local polynomial and local constant litting schemes to estimate the smooth coefficients in a quantile framework. We establish the asymptotic properties of both the local polynomial and local constant estimators for alpha-mixing time series. We also suggest a bandwidth selector based on the nonparametric version of the Akaike information criterion. along with a consistent estimate of the asymptotic covariance matrix. We evaluate the asymptotic behaviors of the estimators at boudaries and compare the local polynomial quantile estimator and the local constant estimator. A simulation study is carried out to illustrate the performance of estimates. An empirical application of the model to real data further demonstrate the potential of the proposed modeling procedures.