Online Program Home
  My Program

Abstract Details

Activity Number: 165 - Statistics for Business and Financial Markets
Type: Contributed
Date/Time: Monday, July 31, 2017 : 10:30 AM to 12:20 PM
Sponsor: Business and Economic Statistics Section
Abstract #324904
Title: Estimating Chinese Treasury Yield Curves with Bayesian Smoothing Splines
Author(s): Zhuoqiong He* and Xiaojun Tong and Dongchu Sun
Companies: and China Securities Index Co., Ltd and University of Missouri

This paper is the first to estimate the term structure of Chinese Treasury yield curves with Bayesian smoothing splines. The smoothing spline as a nonparametric regression method has been widely used for fitting smooth curves due to its flexibility and smoothing properties. This paper focuses on developing a Bayesian smoothing spline model under the Partially Informative Normal (PIN) prior for estimating Chinese Treasury yield curves. There are two main differences between our model and the Bayesian smoothing splines proposed by Speckman and Sun (2003). First, we focus on the natural cubic smoothing splines and use an easy computing formula for the precision matrix in the PIN prior. Second, we sample the smoothing parameter by using an efficient algorithm called the ratio-of-uniforms method. Through empirical studies of Chinese Treasury bond yield to maturity data, we demonstrate that our model provides a better fit than the classical parametric models and the penalized spline model.

Authors who are presenting talks have a * after their name.

Back to the full JSM 2017 program

Copyright © American Statistical Association