Keywords
univariate garch, asymmetric effects
Start Date
1-7-2004 12:00 AM
Abstract
In recent decades, the momentum of global environmental protection has culminated in the KyotoAgreement of 1998, placing the limelight on “green” issues. This paper argues that the protection ofenvironmental systems involves a fragile balance between the costs of environment preservation and the profitmotivations of industrialists. In particular, one of the issues that needs to be addressed is the risk pressuresenvironmental industries face in financial markets, where the higher the risk, the more pressure industries areunder to exploit natural resources. Therefore, in order to devise effective environmentally-friendly yeteconomically viable policies, it is crucial to analyse the risks encountered by environmental industries in financialmarkets. The success of the autoregressive conditional heteroskedasticity (ARCH) or generalised ARCH(GARCH) models in explaining the stylised facts of financial asset returns has led to its widespread use in theempirical finance literature. By modelling the time-variation in conditional variances or volatility, the univariateARCH model by Engle (1982) and the GARCH model by Bollerslev (1986) are able to capture the stylizedfeatures of the persistence of volatility, volatility clusters and kurtosis, while extensions of the GARCH modelsuch as the asymmetric GARCH (GJR) model by Glosten, Jagannathan and Runkle (1993) can accommodate theadditional stylized fact that positive and negative shocks have asymmetric effects, whereby a negative shock hasa greater impact on volatility than a positive shock. This paper models the time-varying conditional variances ofthe returns on a variety of environmental industry sectors using the univariate ARMA(1,1)-GARCH(1,1) and theARMA(1,1)-GJR (1,1) models. Our dataset consists of daily returns on seven Australian environmental industrysectors including Gold Mining, Other Mining, Mining Finance, Oil and Gas, Farming and Fishing, Forestry andPaper over their respective time periods. The findings of this paper suggest that the risks faced by environmentalindustries in financial markets are generally well-explained by the ARMA(1,1)-GARCH(1,1); the ARMA(1,1)-GJR(1,1), on the other hand, received much less support due to the lack of asymmetric effects. The log-momentand second moment conditions were also satisfied empirically, implying that moments exist and the QMLE areboth consistent and asymptotically normal. Therefore, inferences of the ARMA(1,1)-GARCH(1,1) estimates canbe used to aid in formulating new “green” and economically viable environmental policies.
Modelling Financial Returns and Volatility Across Environmental Industry Sectors
In recent decades, the momentum of global environmental protection has culminated in the KyotoAgreement of 1998, placing the limelight on “green” issues. This paper argues that the protection ofenvironmental systems involves a fragile balance between the costs of environment preservation and the profitmotivations of industrialists. In particular, one of the issues that needs to be addressed is the risk pressuresenvironmental industries face in financial markets, where the higher the risk, the more pressure industries areunder to exploit natural resources. Therefore, in order to devise effective environmentally-friendly yeteconomically viable policies, it is crucial to analyse the risks encountered by environmental industries in financialmarkets. The success of the autoregressive conditional heteroskedasticity (ARCH) or generalised ARCH(GARCH) models in explaining the stylised facts of financial asset returns has led to its widespread use in theempirical finance literature. By modelling the time-variation in conditional variances or volatility, the univariateARCH model by Engle (1982) and the GARCH model by Bollerslev (1986) are able to capture the stylizedfeatures of the persistence of volatility, volatility clusters and kurtosis, while extensions of the GARCH modelsuch as the asymmetric GARCH (GJR) model by Glosten, Jagannathan and Runkle (1993) can accommodate theadditional stylized fact that positive and negative shocks have asymmetric effects, whereby a negative shock hasa greater impact on volatility than a positive shock. This paper models the time-varying conditional variances ofthe returns on a variety of environmental industry sectors using the univariate ARMA(1,1)-GARCH(1,1) and theARMA(1,1)-GJR (1,1) models. Our dataset consists of daily returns on seven Australian environmental industrysectors including Gold Mining, Other Mining, Mining Finance, Oil and Gas, Farming and Fishing, Forestry andPaper over their respective time periods. The findings of this paper suggest that the risks faced by environmentalindustries in financial markets are generally well-explained by the ARMA(1,1)-GARCH(1,1); the ARMA(1,1)-GJR(1,1), on the other hand, received much less support due to the lack of asymmetric effects. The log-momentand second moment conditions were also satisfied empirically, implying that moments exist and the QMLE areboth consistent and asymptotically normal. Therefore, inferences of the ARMA(1,1)-GARCH(1,1) estimates canbe used to aid in formulating new “green” and economically viable environmental policies.
