Forecasting copper futures volatility under model uncertainty

Abstract

In practice, volatility forecasting under model uncertainty is an important issue. In this paper, the main purpose is to apply the model averaging techniques to reduce volatility model uncertainty and improve volatility forecasting. for the copper futures. Then, various loss functions are employed to assess the forecasting performance. The empirical study results show that the model averaging methods can significantly reduce the uncertainty of forecast. Furthermore, the OLS time-varying weighted model averaging method can achieve the smallest forecasting error and significantly reduce the over-prediction percentage.