Bayesian inference in a Stochastic Volatility Nelson-Siegel model

Authors:
Nikolaus Hautsch;Fuyu Yang
Affiliations:
CASE, CFS, Quantitative Products Laboratory, Berlin, Germany and Institute for Statistics and Econometrics, Humboldt-Universität zu Berlin, Spandauer Str. 1, D-10099, Berlin, Germany;Institute for Statistics and Econometrics, Humboldt-Universität zu Berlin, Spandauer Str. 1, D-10099, Berlin, Germany
Venue:
Computational Statistics & Data Analysis
Year:
2012

Citing 3
Cited 1

Parameterisation and efficient MCMC estimation of non-Gaussian state space models

Computational Statistics & Data Analysis
Factor estimation using MCMC-based Kalman filter methods

Computational Statistics & Data Analysis
Simulation-based Bayesian estimation of an affine term structure model

Computational Statistics & Data Analysis

A Bayesian approach to term structure modeling using heavy-tailed distributions

Applied Stochastic Models in Business and Industry

Quantified Score

Hi-index	0.03

Visualization

Abstract

Bayesian inference is developed and applied for an extended Nelson-Siegel term structure model capturing interest rate risk. The so-called Stochastic Volatility Nelson-Siegel (SVNS) model allows for stochastic volatility in the underlying yield factors. A Markov chain Monte Carlo (MCMC) algorithm is proposed to efficiently estimate the SVNS model using simulation-based inference. The SVNS model is applied to monthly US zero-coupon yields. Significant evidence for time-varying volatility in the yield factors is found. The inclusion of stochastic volatility improves the model's goodness-of-fit and clearly reduces the forecasting uncertainty, particularly in low-volatility periods. The proposed approach is shown to work efficiently and is easily adapted to alternative specifications of dynamic factor models revealing (multivariate) stochastic volatility.