Forecasting oil futures price volatility: New evidence from realized range-based volatility

In this article, we investigate the impacts of jump intensity on the volatility of futures in the oil futures market using the heterogeneous autoregressive model of realized range-based volatility (HAR-RRV) and its extended model. We present several interesting and notable findings. First, short-term investors have larger influences on oil futures price volatility. In addition, negative returns are significant, but the effects of jumps and their intensity (probability) appear to not be significant during the in-sample period. Second, the out-of-sample results statistically support that our proposed models are able to achieve higher forecast accuracy than that of the benchmark in both the statistical and economic senses, especially when including the combination of significant jumps and jump intensity. Third, our findings are strongly robust in various checks, such as different forecasting windows, sampling frequencies, and volatility measures.