A conditional autoregressive range model with gamma distribution for financial volatility modelling

- A conditional autoregressive range model with gamma distribution (GCARR) is proposed.
- The GCARR model can reduce not only the inlier problem but also the outlier problem of the WCARR model.
- Empirical studies show that our GCARR model outperforms the WCARR model on a broad set of stock indices.
- The GCARR model can be used as a better benchmark for modeling the range-based volatility.

The commonly used conditional autoregressive range model with Weibull distribution (henceforth WCARR) suffers from serious inlier problem. We conjecture that this problem is due to a misspecified distribution to the disturbance, and propose a conditional autoregressive range model with gamma distribution (henceforth GCARR) to model the volatility of financial assets. In this paper, we first discuss the theoretical properties of the GCARR model and then compare its empirical performance with the WCARR. Empirical studies are performed on a broad set of stock indices in different countries over different time horizons. Consistent with the conjecture, we find that the GCARR model can reduce not only the inlier problem but also the outlier problem of the WCARR model. The results indicate that our GCARR model describes the dynamics of the range-based volatility better than the WCARR model and thus serves as a better benchmark.