Forecasting Government Bond Risk Premia Using Technical Indicators

Abstract:     
While economic variables have been used extensively to forecast the U.S. bond risk premia, little attention has been paid to the use of technical indicators which are widely employed by practitioners. In this paper, we fill this gap by studying the predictive ability of technical indicators vis-a-vis economic variables. We find that technical indicators have significant both in- and out-of-sample forecasting power. In addition, utilizing information from both technical indicators and economic variables increases substantially the forecasting performances relative to using just economic variables and results economically significant utility gains. Moreover, we find that the economic value of the bond risk premia forecasts are only comparable to that of the equity risk premium forecasts, despite the out-of-sample R-squares in the bond market are more than 10 times greater than those in the stock market.

Number of Pages in PDF File: 40

Keywords: bond risk premium predictability, economic variables, technical analysis, moving-average rules, volume, out-of-sample forecasts, principal components

JEL Classification: C53, C58, G11, G12, G17

working papers series