Abstract We forecast the realized volatilities of China's agricultural commodity futures (corn, cotton, palm, wheat, and soybean) using a set multivariate heterogeneous autoregressive (MHAR) models. consider different error structures to capture co‐movement volatility (co‐volatility) between obtain out‐of‐sample forecasts at daily, weekly, monthly horizons. also global oil as an additional exogenous predictor assess precision based on both statistical economic value measures. The results...

Abstract Extending the popular HAR model with additional information channels to forecast realized volatility of WTI futures prices, we show that machine learning‐generated forecasts provide better forecasting quality and portfolios are constructed these outperform their competing models resulting in economic gains. Analyzing selection process, vary across horizon. Variable produces clusters provides evidence there structural changes regard significance channels.

Abstract This study investigates the potential effects of environmental factors on fluctuations in agricultural commodity futures markets, by constructing a new category daily exogenous predictors related to air pollution, weather, climate change, and investor attention. The empirical results from out‐of‐sample analyses suggest that heterogeneous autoregressive (HAR) model incorporating all these is more likely outperform other HAR‐type models. Additionally, economic evaluations demonstrate...

We develop a Vector Heterogeneous Autoregression model with Continuous Volatility and Jumps (VHARCJ) where residuals follow flexible dynamic heterogeneous covariance structure. employ the Bayesian data augmentation approach to match realised volatility series based on high-frequency from six stock markets. The structural breaks in are captured by an exogenous stochastic component that follows three-state Markov regime-switching process. find markets have higher dependence during turmoil...

This article identifies the breakdowns in covariance of three benchmark crude oil futures markets (WTI, Brent and Dubai) investigates changes market connectedness across breakdown periods. As are traded different regions, this eliminates non-synchronous trading data by employing Vector Moving Average structure Bayesian augmentation approach, which keeps integrity original without changing its properties. The results show that there significant breaks markets. periods consistent with when...

This article investigates the linear and non-linear dependence structures of risk contagions between global crude oil futures markets China's agricultural based on a regime switching skew-normal (RSSN) model. We examine oil-agriculture relationships identify contagion channels under calm turbulent market conditions. The directions are further identified with directed acyclic graph (DAG) from non-Gaussian models algorithm. empirical results tests show significance correlation covariance...

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

Jiawen Luoa & Langnan Chen*ba School of Business Administration, South China University Technology, Guangzhou, P.R. Chinab Lingnan (University) College, Sun Yat-sen University,

Abstract We investigate the realised volatility (RV) forecasts for short, mid, and long term by developing HAR models with Bayesian approaches employing high-frequency data of China Stock Index 300 (CSI300) future period from 16 April 2010 to 21 May 2014. also evaluate performances competing both in-sample out-of-sample forecasts. find that proposed HAR-type capture time-varying properties parameters predictor sets. have superior forecast performance as compared benchmark models.

We construct a set of HAR models with three types infinite Hidden Markov regime switching structures. Particularly, jumps, leverage effects, and speculation effects are taken into account in realized volatility modeling. forecast five agricultural commodity futures (Corn, Cotton, Indica Rice, Palm oil Soybean) based on high frequency data from Chinese markets evaluate the performances both statistical economic evaluation measures. The results suggest that structures have better precision...