Multivariate realized volatility forecasts of agricultural commodity futures

Abstract

We forecast the multivariate realized volatility of agricultural commodity futures by constructing multivariate heterogeneous autoregressive (MHAR) models with flexible heteroscedastic error structures that allow for non‐Gaussian distribution, stochastic volatility, and heteroscedastic and serial dependence. We evaluate the forecast performances of various models based on both statistical and economic criteria. The in‐sample and out‐of‐sample results suggest that the proposed MHAR models allowing for flexible heteroscedastic covariance structures outperform the benchmark MHAR models. In addition, the proposed Bayesian MHAR models allowing for t innovations improve both in‐sample and out‐of‐sample forecast performance of the corresponding MHAR models with Gaussian innovations.

Forecasting the volatility of agricultural commodity futures: The role of co‐volatility and oil volatility

“…The specification of the common‐volatility for the MHAR‐CSV model and the MHAR‐CSV‐t models introduces extra information of the co‐movement of agricultural commodity futures, which results in the better forecast performances of these two models. This finding is consistent with those in Carriero et al (2016), Luo and Chen (2019) and Chan (2020).…”

“…The introduction of extra information from the co‐movement of commodity futures can also improve forecast accuracy, which has been proven in some research (e.g., Carriero et al, 2016; Chan, 2020). Second, specifying the HAR models with heteroscedastic and flexible error structures can lead to better portfolio performances, as shown in Luo and Chen (2019). Thus, the HAR model with co‐volatility provides surpluses in portfolio returns.…”

“…Existing research shows that the discovery of biofuels, food crisis episodes, and commodity financialization have led to a spillover of risks and co‐movement between different agricultural commodities (particularly wheat, corn, soybeans, and sugar) as well as within the energy sector (Du et al, 2011; Natanelov et al, 2011; Nazlioglu et al, 2013; Tyner, 2010). Forecasting the volatility of commodity price futures is vital for identifying drivers of the commodities market and managing associated risks (Ji & Fan, 2016; Ji et al, 2018; Klein, 2018; Klein & Walther, 2016; Luo & Chen, 2019; Luo, Chen, et al, 2019; Ma et al, 2019; Nazlioglu et al, 2013; Tian et al, 2017a, 2017b; Todorova et al, 2014; Walther & Nguyen, 2018).…”