Estimating Value At Risk Of Carbon Trading Market: Conditional Autoregressive Value At Risk Models With Refinements From Extreme Value Theory

The international carbon market provides an effective and important way to cope with climate change and environmental problems for countries in the world. The price of carbon assets fluctuates heavily because of the global economy, politics, energy, and so on, thus it has been of theoretical and realistic significance to have research on the risk measurement of carbon market.This paper takes EUA and CER which are the most representative carbon assets as the research objects, and the EUA and CER future market at consecutive contracts trading prices are as the data sample. The time window of the sample for our study is from 14 March 2008 to 31 December 2012 which gives us approximately the whole second commitment period of data. The description of data shows the extreme behaviors of the return series. We proposes a way of quantile regression from Conditional Autoregressive Value at Risk (CAViaR) models to predict different quantiles of tail risk, which is compared with the widely used GARCH-GED model. The out-of-sample data is divided into two prediction intervals in order to contrast the forecast performances of different periods with different volatilities. We find that CAViaR model is better than GARCH-GED model in fitting and prediction. But the CER market trading mechanism and maturity remains to be further perfected and improved, having a greater uncertainty compared to the EUA market, which lead to a worse prediction performance of the CAViaR models. And when predicting 1% VaR, it is also instable.In hope of a better prediction effect, this paper takes the combination of CAViaR models and extreme value theory to predict 1% VaR, finding that the prediction of EVT-CAViaR models is more steady and reliable under the high-risk prediction intervals and the CER market, therefore we can make a conclusion that this new method promises to partly improve the prediction accuracy of the extreme risk of carbon markets.The study of this paper enriched the econometric models for the risk measurement of carbon market, which also provided some theoretical evidence for risk avoidance and policymaking.