由於氣候衍生型商品快速的發展，每日平均天氣模型被廣泛的研究與討論。 Campbell and Diebold (2005) 利用包含季節性變動的GARCH模型來配適美國城市的天氣。 我們用不同的copula 做連結並應用在亞洲城市上來描述城市之間的天氣的相關性。 在本篇論文中，我們透過模擬去論證我們的預測方法以及亞洲城市的每日平均資料去做實例分析。

Because of the rapid development of weather derivatives, models for daily average temperature have been extensively studied in the literature. citet{dat} provide a time series model with a GARCH model for the volatility to describe the features for modelling daily average temperature in U.S. cities. Motivated by Campbell and Diebold (2005), we apply this model in Asian cities and use trivariate fully nested Archimedean Gumbel and Clayton copula to describe the dependence structure for the error distribution.
To show the superiority of our model, we construct the prediction interval for the one-year ahead daily average temperature data using eight-year historical data, and show the coverage rates are higher when the dependence structure is employed.

Alaton, P., B. Djehiche, and D. Stillberger (2002). On modelling and pricing weather
derivatives. Applied Mathematical Finance 9, 1–20.
Benth, F. E. and J. ˆSaltyt˙e Benth (2005a). Stochastic modelling of temperature variations
with a view towards weather derivatives. Applied Mathathematical Finance 12, 53–85.
Benth, F. E. and J. ˆSaltyt˙e Benth (2005b). The volatility of temperature and pricing of
weather derivatives. Pure Mathematics, Preprint, Department of Mathematics, Univerity
of Oslo.
Campbell, S. and F. Diebold (2005). Weather forecasting for weather derivatives. Journal
of American Statistical Association 100, 6–16.
Caporin, M. and J. Pre’s (2009). Forecasting temperature indices with time-varying longmemory
models. Marco Fanno working paper N.88, 1–58.
Engle, R. (2002). Dynamic conditional correlation: a simple class of multivariate generalized
autoregressive conditional heteroskedasticity models. Journal of Business and
Economic Statistics 20, 339–350.
Engle, R. and K. Kroner (1995). Multivariate simultaneous generalized ARCH. Econometric
Theory 11, 122–50.
H‥ardle, W. K. and B. L’opez-Cabrera (2009). Implied market price of weather risk (2009-
001). SFB 649, Humboldt-Universit‥at zu Berlin Spandauer.
Lee, T.-H. and X. Long (2009). Copula-based multivariate GARCH model with uncorrelated
dependent errors. Journal of Econometrics 150, 207–218.
Luca, G. D. and G. Rivieccio (2008). Measuring tail dependence with a Copula-GARCH
model. Department of Statistics and Mathematics for Economic Research, University
of Napoli Parthenope, via Medina 40, 80133 Napoli, Italy.
Makridakis, S., S. C. Wheelwright, and R. J. Hyndman. (1998). Forecasting:methods and
applications. New York: John Wiley & Sons.
McNeil, A. J. (2008). Sampling nested Archimedean copulas. Journal of Statistical
Computation and Simulation 78, 567–581.
Mraova, M. and D. Bari (2007). Temperature stochastic modelling and weather deriatives
pricing: empirical study with moroccan data. Afrika Statistika 2, 22–43.
Okhrin, O., Y. Okhrin, and W. Schmid (2009). Properties of Hierarchical Archimedean
copulas (2009-014). SFB 649, Humboldt-Universit‥at zu Berlin.
Patton, A. J. (2011). Copula methods for forecasting multivariate time series. Handbook
of Economic Forecasting Vol. 2 Elsevier, Oxford.
Pellegrini, S., E. Ruiz, and A. Espasa (2011). Prediction intervals in conditionally heteroscedastic
time series with stochastic components. International Institute of Forecasters
27, 308–319.
Shumway, R. H. and D. S. Stoffer (2006). Time Series Analysis and Its Applications :
With R Examples. New York: Springer.
Sklar, A. (1959). Fonctions de r’epartition `an dimensions et leurs marges. Publications de
Institut Statistique de Universite de Paris 8, 229–231.
Tse, Y. and A. Tsui (2002). A multivariate generalized autoregressive conditional heteroscedasticity
model with time-varying correlations. Journal of Business and Economic
Statistics 20, 351–362.