Range-based volatility forecasting: an extended conditional autoregressive range model

Abstract

This paper proposes an extended conditional autoregressive range (EXCARR) model to describe the range-based volatility dynamics of financial assets. Our EXCARR model not only takes the conditional autoregressive range (CARR) model as a special case but also considers the asymmetry between the upward range and the downward range. Empirical studies performed on a variety of stock indexes show that the EXCARR model outperforms not only the CARR model but also the asymmetric CARR (ACARR) model in both in-sample and out-of-sample forecasting. Hence, our EXCARR model provides a new benchmark for range-based volatility forecasting.