Australian Journal of Agricultural and Resource Economics · 2016 · 13 citations · 25 references
AgricultureEconomicsNatural Resource EconomicsCommodity MarketsEconometricsTime Series AnalysisCommodity Price DynamicsCommodity Price ForecastingCommodity Price RiskFutures MarketsRenewable EnergyVolatility ModelingCommodity Price Time Series AnalysisConditional Heteroskedasticity ModelsCrude Oil MarketsFutures Price VolatilityGeneralized Autoregressive Conditional Heteroskedasticity ModelsOil Price VolatilityResource Price VolatilitySmooth Transition Autoregressive Models
This study outlines a new approach for differentiating commodity futures based on their exhaustibility. Various aspects of volatility in the futures prices of renewable resources (palm oil, coffee, soya beans, rice, wheat and corn) and nonrenewable resources (zinc, aluminium, natural gas, gold, crude oil and copper) are studied, exploring whether volatility is greater in the former than in the latter. We use a generalised autoregressive conditional heteroskedasticity (GARCH) model to test our main hypothesis that the volatility in futures prices for renewable resources has recently been equal to or greater than the volatility in futures prices for nonrenewable resources. Our key findings suggest that futures prices for some renewable resources have greater variance than those for benchmark crude oil in a simulated GARCH series. We extend our analysis using a nonlinear vector smooth transition autoregressive (VSTAR) model to test for the existence of a shifting-mean tendency in the commodity series that we researched. We show that transition from a stable to a volatile regime is more abrupt for renewable resources.
25
Generalized autoregressive conditional heteroskedasticity
Tim Bollerslev · Journal of Econometrics · 1986 · 22.3K citations · Full text
Business, Finance, Econometrics +11
Index Investment and the Financialization of Commodities
Ke Tang, Wei Xiong · Financial Analysts Journal · 2012 · 1.3K citations