What causes price volatility and regime shifts in the natural gas market

被引:51
作者
Lin, Boqiang [1 ,2 ]
Wesseh, Presley K., Jr. [2 ]
机构
[1] Minjiang Univ, New Huadu Business Sch, Fuzhou 350108, Peoples R China
[2] Xiamen Univ, Coll Econ B201, China Ctr Energy Econ Res, Xiamen 361005, Peoples R China
关键词
Natural gas price; Regime-switching; Volatility forecasts; AUTOREGRESSIVE CONDITIONAL HETEROSKEDASTICITY; CARLO MAXIMUM-LIKELIHOOD; OIL-PRICE; STOCHASTIC VOLATILITY; TIME-SERIES; GARCH MODELS; STOCK-MARKET; ARCH MODELS; RISK; VARIANCE;
D O I
10.1016/j.energy.2013.03.082
中图分类号
O414.1 [热力学];
学科分类号
摘要
Gas sector volatility is of interest because it affects decisions made by producers and consumers and also influences investors' decision in gas-related investments, portfolio allocation and risk management. This paper therefore attempts to explain the behavior of natural gas index returns and in so doing proposes application of a pure Markov-switching volatility model whose variance is subject to shift in regime. We show that regime-switching is clearly present in the natural gas market and such should not be ignored. All ARCH effects that show up in weekly natural gas index returns data die out almost completely after allowing for Markov-switching variance. Volatility regimes identified by our model correlate well with major events affecting supply and demand for natural gas. Out-of-sample tests indicate that the regime switching model performs noticeably better than a wide range of volatility models considered regardless of evaluation criteria, thus providing a better framework for the policy maker or financial historian interested in studying factors behind the evolution of volatility and to natural gas futures traders interested in short-term volatility forecasts. As risk-hedging decisions rely critically on assumptions about volatility, policies based on the transition probabilities are likely to be more conservative. (C) 2013 Elsevier Ltd. All rights reserved.
引用
收藏
页码:553 / 563
页数:11
相关论文
共 66 条
[3]   BAYES INFERENCE VIA GIBBS SAMPLING OF AUTOREGRESSIVE TIME-SERIES SUBJECT TO MARKOV MEAN AND VARIANCE SHIFTS [J].
ALBERT, JH ;
CHIB, S .
JOURNAL OF BUSINESS & ECONOMIC STATISTICS, 1993, 11 (01) :1-15
[4]   Value-at-risk estimations of energy commodities via long-memory, asymmetry and fat-tailed GARCH models [J].
Aloui, Chaker ;
Mabrouk, Samir .
ENERGY POLICY, 2010, 38 (05) :2326-2339
[5]  
Alterman S., 2012, Natural Gas Price Volatility in the UK and North America
[6]  
Anderson HM., 1999, NONLINEAR TIME SERIE, P191, DOI DOI 10.1007/978-1-4615-5129-4_10
[7]   On the impacts of oil price fluctuations on European equity markets: Volatility spillover and hedging effectiveness [J].
Arouri, Mohamed El Hedi ;
Jouini, Jamel ;
Duc Khuong Nguyen .
ENERGY ECONOMICS, 2012, 34 (02) :611-617
[8]  
AUG A, 2002, J BUSINESS EC STAT, V20, P163
[9]   Fractionally integrated generalized autoregressive conditional heteroskedasticity [J].
Baillie, RT ;
Bollerslev, T ;
Mikkelsen, HO .
JOURNAL OF ECONOMETRICS, 1996, 74 (01) :3-30
[10]   GENERALIZED AUTOREGRESSIVE CONDITIONAL HETEROSKEDASTICITY [J].
BOLLERSLEV, T .
JOURNAL OF ECONOMETRICS, 1986, 31 (03) :307-327