Forecasting the Term Structure of Government Bond Yields in Unstable Environments

53 Pages Posted: 5 May 2015 Last revised: 16 Sep 2019

See all articles by Joseph Byrne

Joseph Byrne

Heriot-Watt University - Department of Accountancy, Economics and Finance

Shuo Cao

Shenzhen Stock Exchange; City University of Hong Kong (CityUHK)

Dimitris Korobilis

University of Glasgow - Adam Smith Business School

Date Written: September 30, 2017

Abstract

In this paper we model and predict the term structure of US interest rates in a data-rich and unstable environment. The dynamic Nelson-Siegel factor model is extended to allow the model dimension and the parameters to change over time, in order to account for both model uncertainty and sudden structural changes, in one setting. The proposed specification performs better than several alternatives, since it incorporates additional macro-finance information during hard times, while it allows for more parsimonious models to be relevant during normal periods. A dynamic variance decomposition measure constructed from our model shows that parameter uncertainty and model uncertainty regarding different choices of predictors explain a large proportion of the predictive variance of bond yields.

Keywords: Term Structure of Interest Rates; Nelson-Siegel; Dynamic Model Averaging; Bayesian Methods; Term Premia

JEL Classification: C32; C52; E43; E47; G17

Suggested Citation

Byrne, Joseph and Cao, Shuo and Korobilis, Dimitris, Forecasting the Term Structure of Government Bond Yields in Unstable Environments (September 30, 2017). Available at SSRN: https://ssrn.com/abstract=2602501 or http://dx.doi.org/10.2139/ssrn.2602501

Joseph Byrne

Heriot-Watt University - Department of Accountancy, Economics and Finance ( email )

Scotland
United Kingdom

Shuo Cao

Shenzhen Stock Exchange ( email )

2012 Shennan Blvd., Futian District
Shenzhen
China

City University of Hong Kong (CityUHK) ( email )

83 Tat Chee Avenue
Kowloon
Hong Kong

Dimitris Korobilis (Contact Author)

University of Glasgow - Adam Smith Business School ( email )

40 University Avenue
Gilbert Scott Building
Glasgow, Scotland G12 8QQ
United Kingdom

HOME PAGE: http://https://sites.google.com/site/dimitriskorobilis/

Register to save articles to
your library

Register

Paper statistics

Downloads
352
Abstract Views
1,600
rank
86,559
PlumX Metrics