Range-based volatility forecasting: a multiplicative component conditional autoregressive range model

Abstract

To capture the effect in volatility, a multiplicative component conditional autoregressive range (MCCARR) model is proposed. We show theoretically that the MCCARR model can capture the long-memory effect well. An empirical study is performed on the Standard & Poor's 500 index, and the results show that the MCCARR model outperforms both conditional autoregressive range and heterogeneous autoregressive models for in-sample and out-of-sample volatility forecasting.