Predicting short-term interest rates using Bayesian model averaging: evidence from weekly and high frequency data

Authors

Chew Lian Chua, University of Melbourne
Sandy Suardi, University of WollongongFollow
Sarantis Tsiaplias, Predictive Analytics Group

RIS ID

97740

Publication Details

Chua, C., Suardi, S. & Tsiaplias, S. (2013). Predicting short-term interest rates using Bayesian model averaging: evidence from weekly and high frequency data. International Journal of Forecasting, 29 (3), 442-455.

Abstract

This paper examines the forecasting performance of Bayesian model averaging (BMA) for a set of single factor models of short-term interest rates. Using weekly and high frequency data for the one-month Eurodollar rate, BMA produces predictive likelihoods that are considerably better than those associated with the majority of the short-rate models, but marginally worse than those of the best model in each dataset. We also find that BMA forecasts based on recent predictive likelihoods are preferred to those based on the marginal likelihood of the entire dataset.