The VEC-NAR model for short-term forecasting of oil prices

The prediction of future crude oil prices is highly challenging due to three characteristics of crude oil prices, namely, their lag, nonlinearity, and interrelationship among different oil markets, which cannot be handled simultaneously by most traditional crude oil price forecasting models. This paper proposes a new hybrid vector error correction and nonlinear autoregressive neural network (VEC-NAR) model to deal with these characteristics simultaneously. Firstly, a VEC model is used to optimize the lag of crude oil prices and determine the interrelationship which distinguishes the endogenous and exogenous variables. Then, the optimal results obtained by the VEC model are combined with a NAR model which effectively depicts nonlinear component, to forecast crude oil prices. The data of Brent oil prices from January 1, 2003 to December 31, 2014 were used as the empirical sample to test the effectiveness of our proposed model which is compared with those well-recognized methods for crude oil price forecasting. The results of Diebold-Mariano test demonstrated that the VEC-NAR model provided superior forecasting accuracy to traditional models such as GARCH class models, VAR, VEC and NAR model in multi-step ahead short-term forecast.     

Do high-frequency stock market data help forecast crude oil prices? Evidence from the MIDAS models

Extensive studies have used stock market information to forecast crude oil prices, and stock market can more easily derive high-frequency data than crude oil market due to no revisions, which raises a question that whether high-frequency stock market data can improve the forecast performance of crude oil prices. Therefore, this paper employs the MIDAS model and the high-frequency data of four stock market indices to forecast WTI and Brent crude oil prices at lower frequency. The results indicate that the high-frequency stock market indices have certain advantage over the lower-frequency data in forecasting monthly crude oil prices, and the MIDAS model using high-frequency data proves superior to the ordinary model.     

The role of trader positions in spot and futures prices for WTI

We extend the analysis of causal relations between trader positions and oil prices and the process of price discovery by estimating a cointegrating vector autoregression (CVAR) model that expands the cash-and-carry relation between spot and futures prices to quantify long- and short-run relations among oil prices, trader positions, interest rates, and oil inventories. Results indicate that oil inventories and trader positions are needed to generate cointegration between spot and futures prices. The presence of trader positions and oil inventories suggest that both play a role in price discovery. Furthermore, the cointegrating relation for price loads into the equation for both oil prices and trader positions. This suggests a bi-directional simultaneous adjustment process between oil prices and trader positions. This expands the unidirectional causal relation from oil prices to trader positions that is generated by previous studies. Additional results suggest that price discovery occurs in the market for heavily traded near-month futures contracts, but discovery for thin far-month futures markets occurs in the spot market. Together, these results suggest mechanisms by which speculation could affect oil prices but the results presented here are moot regarding their effects.     

基于金融衍生品的中国原油进口策略研究

中国原油进口逐年增长,石油对外依存度不断提高,早已超过50%这一国际警戒线。为解决面对采购方式选择种类多、不确定因素多的局面以及原油定价权的缺失、深陷亚洲溢价、买涨不买跌等问题,通过对中国与世界原油进口数据进行研究,运用统计学回归分析方法理论建立了中国原油进口量预测模型;在中国未来原油进口量预测基础上,结合国际上对原油期货价格的预期,对中国原油进口市场及投资方式进行对比选择;比较了各类投资方式的VAR风险值计算结果数据。结果表明,中国原油进口在现货采购的同时,采用原油期货与外汇期货组合投资更有利于规避风险。研究了国际原油期货市场交易规则,运用历史模拟与线性规划混合分析的方法,在对未来原油期货与外汇期货可能出现的情形预测下,采用线性规划方法对各不同可能情形下的组合投资进行比例分配;在风险规避的原则下,达到满足原油进口需求与优化资金使用的双重要求,最终得到一条符合中国发展现状的原油进口采购路径。     

The role of underground storage in the dynamics of the US natural gas market: A threshold model analysis

Natural gas is an important source of energy in the global economy, hence understanding the drivers of its prices is of significant interest for the many economic agents. This paper investigates the role of inventories for the dynamics of the U.S. natural gas market. Our contribution is twofold. First, within the threshold structural VAR framework we demonstrate that in a low inventory regime spot prices are more responsive to economic fundamentals in comparison to situation in which the inventories are high. Second, we present evidence that the level of natural gas inventories have a significant effect on the relationship between spot and futures prices.     

Asymmetry in retail gasoline and crude oil price movements in the United States: An application of hidden cointegration technique

There is a common belief that gasoline prices respond more quickly to crude oil price increases than decreases. Some economists and politicians believe that asymmetry in oil and gasoline price movements is the outcome of a non-competitive gasoline market requiring that governments take policy action to address “unfair pricing”. There is no consensus as to the existence, or nature, of the asymmetric relationship between prices of gasoline and crude oil. Much of this literature specifies asymmetry in the speed of adjustment and short-run adjustment coefficients. In contrast, Granger and Yoon's [Granger, C.W. and Yoon, G. “Hidden Cointegration”, University of California, San Diego, Department of Economics Working Paper, (2002).] Crouching Error Correction Model (CECM) identifies asymmetry of the cointegrating vectors between components (cumulative positive and negative changes) of the series. Applying the CECM to retail gasoline and crude oil prices for the U.S., we find that there is only evidence of cointegration between positive components of crude oil prices and negative components of gasoline prices. In contrast to the literature which attributes asymmetric price movements to market power of refiners, these findings suggest that gasoline prices –in the long run– are more influenced by the technological changes on the demand side than crude oil price movements on the supply side.     

The role of market fundamentals and speculation in recent price changes for crude oil

I hypothesize that the price spike and collapse of 2007–2008 are driven by both changes in both market fundamentals and speculative pressures. Contrary to arguments for a demand shock, I hypothesize that prices rise sharply in 2007–2008 because ongoing growth in Chinese oil demand runs into a sudden and unexpected halt to a decade long increase in non-OPEC production. This caused a loss of OPEC spare capacity because increased demand for OPEC production runs ahead of increases in OPEC capacity. These changes are reinforced by speculative expectations. Although difficult to measure directly, I argue for the role of speculation based on the following: (1) a significant increase in private US crude oil inventories since 2004; (2) repeated and extended break-downs (starting in 2004) in the cointegrating relationship between spot and far month future prices that are inconsistent with the law of one price and arbitrage opportunities; and (3) statistical and predictive failures by an econometric model of oil prices that is based on market fundamentals. These changes are related to the behavior and impact of noise traders on asset prices to sketch mechanisms by which speculative expectations can affect crude oil prices.     

通过匹配原油计价量与加工量规避原油计价风险的探讨

进口原油具有的贸易特点及计价方法,与炼油企业当期销售成品油的计价方法不同,造成原油与成品油计价期不同,在国际油价剧烈波动,特别是油价快速下跌时,使炼油企业严重亏损。当企业均衡生产时,这种时间差带来的市场风险会通过装置长周期运行而减小,但当企业的加工和采购进度因装置检修、非计划停工以及市场供需调整等原因进行大幅调整时,成本和产品价格之间的时间差可能会给企业带来巨大风险。分别介绍了进口原油、成品油的贸易特点及计价方法,提出了如何研究国际油价走势。分析了国际油价上涨时,如何选择原油计价期,实现低价采购原油、高价销售成品油的目标;国际油价下跌时,如何实现同期原油计价量与原油加工量匹配,实现均衡计价,规避因国际油价波动造成的企业亏损,进一步剖析了如何运用套期保值方法,锁定当期炼油企业原油加工效益。同时,列举了操作中的注意事项,提出套期保值应善于选择时机操作,加强计划管理的重要性,以及控制合理库存的必要性。     

Stockpile strategy for China׳s emergency oil reserve: A dynamic programming approach

China is currently accelerating construction of its strategic petroleum reserves. How should China fill the SPR in a cost-effective manner in the short-run? How might this affect world oil prices? Using a dynamic programming model to answer these questions, the objective of this paper is to minimize the stockpiling costs, including consumer surplus as well as crude acquisition and holding costs. The crude oil acquisition price in the model is determined by global equilibrium between supply and demand. Demand, in turn, depends on world market conditions including China׳s stockpile filling rate. Our empirical study under different market conditions shows that China׳s optimal stockpile acquisition rate varies from 9 to 19 million barrels per month, and the optimal stockpiling drives up the world oil price by 3–7%. The endogenous price increase accounts for 52% of total stockpiling costs in the base case. When the market is tighter or the demand function is more inelastic, the stockpiling affects the market more significantly and pushes prices even higher. Alternatively, in a disruption, drawdown from the stockpile can effectively dampen soaring prices, though the shortage is likely to leave the price higher than before the disruption.     

On the relation between global food and crude oil prices: An empirical investigation in a nonlinear framework

The research explores the dynamic relationship between global crude oil price and food price indices on a sample of monthly data spanning from January 1990 to June 2017 within a nonlinear framework. Linear methods are applied first to examine the stationarity, co-integration and linear Granger causality of the variables of crude oil and food price indices. Moreover, a series of nonlinear tests are used to detect the nonlinearity of the univariate and oil-food prices link. Finally, the asymmetric adjustment analyses are made to understand the dynamic vary mechanism depending on the considered regime of the threshold vector autoregressive model (TVAR), and the threshold vector error correction model (TVECM) is integrated to check how the variables respond to the deviations from the equilibrium. The findings of systematic tests and analyses confirm the fact that there is a nonlinear causal relationship between global crude oil and food price indices. The co-movement of crude oil and food price has obvious structural break features, which is relevant to the underlying regime. Furthermore, the results also show that the adjustment process of the food price indices towards equilibrium is highly persistent and grows faster than oil price when a threshold is reached.     

Assessment of the relationship between oil prices and US oil stocks

This paper qualitatively and quantitatively analyzes the relationship between US monthly ending oil stocks position with that of West Texas Intermediate (WTI) oil prices from February 1995 to July 2004. The paper concludes if other things are held constant, WTI is inversely related to the petroleum products (PPP), combined petroleum products and crude oil (CPPP), crude oil alone (Crude), total oil stocks including petroleum products, crude oil and strategic petroleum reserves SPR (Total), total gasoline (TGO), total distillate (TDO). It could not establish a statistically significant and negative relationship with SPR when run alone. One percent increase (decrease) in CPPP, PPP, Crude, Total, TGO and TDO leads to decrease (increase) in WTI, respectively, by 0.70, 0.43, 0.37, 0.97, 0.26 and 0.21 percent. Oil prices are largely influenced by total crude and Crude and PPP inventories levels while modestly with variations in gasoline and distillate stocks levels. Despite a healthy increase of over 22 percent in SPR from January 2001 to April 2004, it did not result in easing of oil prices. Primarily because SPR are meant for security of supply concern and are only released under extreme conditions by the President of United States, they are neither meant for the purposes of balancing supply–demand gap nor for the stability of oil prices. The aggressive SPR buildup in recent years is related to international terrorism, geopolitical situation in the Middle East, particularly in Iraq, that encourages US government to enhance its SPR to meet any short-term eventuality. The analyst must keep a close eye on CPPP and the total oil stocks variation to forecast WTI in the short run whilst gasoline and distillate influence oil prices modestly in the short run. SPR, on the other hand, are expected to play a pivotal role in balancing oil prices and in providing a critical resource for the economy in case of any major shortfall in the long run.     

Time-frequency contained co-movement of crude oil and world food prices: A wavelet-based analysis

This paper evaluates the association between crude oil prices and world food price indices, first within general space and time, and then within the combined time-frequency sphere. Monthly price data spanning from January 1990 to February 2016 were used for the analysis. The Johansen cointegration test conducted within the time domain confirmed the statistically significant cointegrated relationship between crude oil prices and the price indices of food and its sub-categories, such as dairy, cereals, vegetable oil, and sugar; however, frequency information was not accounted for. To incorporate both the time and frequency features of the data, we used a wavelet method that has shown that the world food prices, along with the prices of cereals, vegetable oils, and sugar, co-move with and are led by crude oil prices, results that remain relevant from the short-run policy perspective. The outcome of Toda–Yamamoto causality confirmed the spillover of crude oil price changes to the world food price index also in the long run. The paper ends with the policy implications of these results.     

Crude inventory accounting and speculation in the physical oil market

This paper uses inventory data from financial accounts to explore whether companies involved in the physical oil market were speculating in the run-up to 2008. Using quarterly inventory data over the period 1990Q4 to 2012Q1 and a sample of 15 of the largest listed oil companies in the world, we derive an Index of Scaled Physical Inventories (ISPI). We find declining ISPI up to the early 2000s is consistent with firms minimizing inventory for efficiency sake; then ISPI starts to increase, suggesting physical inventories could have contributed to the run-up in oil prices between 2003 and 2008. Highlighting heterogeneity in inventory behaviors amongst the large oil companies, the structural break test on the ratio of inventory to sales and the days to sales for individual companies shows that five companies had positive structural breaks during the speculation period, while the other companies had no or negative structural breaks. Contrary to declining inventory expectations due to a tightening oil market, the positive structural breaks suggest speculative behavior. We also examine the relationship between changes in profitability and changes in oil inventory over the pre-speculation and speculation period. Though some coefficients for inventory do switch from negative to positive over the two periods as hypothesized, they are only significant in a few cases. However, aggregate measures of inventory do switch and are significant, suggesting that, on average, inventory holdings negatively affected profitability in the pre-speculation period and positively affected profitability in the speculation period.     

Influential factors in crude oil price forecasting

This paper identifies factors that are influential in forecasting crude oil prices. We consider six categories of factors (supply, demand, financial market, commodities market, speculative, and geopolitical) and test their significance in the context of estimating various forecasting models. We find that the Least Absolute Shrinkage and Selection Operator (LASSO) regression method provides significant improvements in the forecasting accuracy of prices compared to alternative benchmarks. Relative to the no-change and futures-based models, LASSO forecasts at the 8-step ahead horizon yield significant reductions in Mean Squared Prediction Error (MSPE), with MSPE ratios of 0.873 and 0.898, respectively. We also document substantial improvements in forecasting performance of the factor-based model that employs only a subset of variables chosen by LASSO. Finally, the time-varying nature of the relationship between factors and oil prices is used to explain recent movements in crude oil prices.     

Factors affecting the carbon allowance market in the US

The US carbon allowance market has different characteristic and price determination process from the EU ETS market, since emitting installations voluntarily participate in emission trading scheme. This paper examines factors affecting the US carbon allowance market. An autoregressive distributed lag model is used to examine the short- and long-run relationships between the US carbon allowance market and its determinant factors. In the long-run, the price of coal is a main factor in the determination of carbon allowance trading. In the short-run, on the other hand, the changes in crude oil and natural gas prices as well as coal price have significant effects on carbon allowance market.     

Price and income elasticities of crude oil import demand in South Africa: A cointegration analysis

This paper examines the demand for imported crude oil in South Africa as a function of real income and the price of crude oil over the period 1980–2006. We carried out the Johansen co integration multivariate analysis to determine the long-run income and price elasticities. A unique long-run cointegration relationship exists between crude oil imports and the explanatory variables. The short-run dynamics are estimated by specifying a general error correction model. The estimated long-run price and income elasticities of −0.147 and 0.429 suggest that import demand for crude oil is price and income inelastic. There is also evidence of unidirectional long-run causality running from real GDP to crude oil imports.     

Long-term forecasts for energy commodities price: What the experts think

The ability to forecast energy prices in the long-term is important for a wide range of reasons, from the formulation of countries' energy and transportation policies to the defensive strategies of nations to investment decisions within the private sector. Despite the importance of these predictions, however, forecasters and market pundits face a difficult challenge when trying to forecast over the long-term. While statistical models can credibly rely on assumptions about the relationship between variables in the short-term, they are frequently less reliable in the long-term as political and technological transformations profoundly change how the economy works over time. Towards improving long-term predictions for energy commodities, this paper uses the elicitation and aggregation of experts' beliefs to put forward forecasts for crude oil and natural gas prices by incentivizing experts to tell the truth and minimising their own biases through the application of the Bayesian Truth Serum. With this approach, we generated both short-term and long-term forecasts, and used the short-term forecast to validate the quality of the experts' predictions.     

Another perspective on gasoline price responses to crude oil price changes

The effects of oil price volatility on the responses of gasoline prices to oil price shocks have received little attention in discussions on the relationship between the prices of crude oil and gasoline. In this paper we consider such effects by using a bivariate structural vector autoregression which is modified to accommodate GARCH-in-mean errors. Our measure of oil price volatility is the conditional variance of the oil price–change forecast error. We isolate the effects of volatility in the price of oil on the price of gasoline and employ simulation methods to calculate nonlinear impulse response functions (NIRFs) to trace any asymmetric effects of independent oil price shocks on the conditional means of gasoline prices. We test whether the relationship between the prices of crude oil and gasoline is symmetric using tests of the null hypothesis of symmetric impulse responses. Based on monthly U.S. data over the period from 1978:1 to 2014:11, our empirical results show that gasoline prices respond asymmetrically to positive and negative oil price shocks. We also find that oil price volatility has a positive effect on the price of gasoline and it contributes to the asymmetries in the transmission of oil price shocks.     

Short-run and long-run elasticities of import demand for crude oil in Turkey

The aim of this study is to attempt to estimate the short-run and the long-run elasticities of demand for crude oil in Turkey by the recent autoregressive distributed lag (ARDL) bounds testing approach to cointegration. As a developing country, Turkey meets its growing demand for oil principally by foreign suppliers. Thus, the study focuses on modelling the demand for imported crude oil using annual data covering the period 1980–2005. The bounds test results reveal that a long-run cointegration relationship exists between the crude oil import and the explanatory variables: nominal price and income, but not in the model that includes real price in domestic currency. The long-run parameters are estimated through a long-run static solution of the estimated ARDL model, and then the short-run dynamics are estimated by the error correction model. The estimated models pass the diagnostic tests successfully. The findings reveal that the income and price elasticities of import demand for crude oil are inelastic both in the short run and in the long run.     

Inventory theory in cartelized markets

This paper extends conventional price and inventory theory into the realm of cartelized markets. The motives for holding inventories are classified as speculative, precautionary and transactions, and each is analysed theoretically and empirically for competitive and cartelized markets. The magnitudes of the speculative demands for crude oil and refined products are estimated using US data. However, the models and empirical techniques are applicable to any nation or region. An important finding is that trends in prices, production, consumption and inventory levels are likely to be remarkably different in competitive and cartelized markets.