在過去二十幾年當中，世界各地電力市場紛紛走上自由化的道路，在自由競爭的環境下，市場生產者與消費者所承擔的風險相對增加。也因此電力現價在波動上產生了幾個模式化事實，尤其是尖峰現象，指的是電價在短時間內顯著地上漲或下跌，隨後又回歸，這特性增加模型解釋的難度。本文也將拿股價做為比較，股價也有類似的特性，但其落下速率比起電價來得慢。
本文將採用兩種模型：均值回歸跳躍擴散模型、馬可夫狀態轉換模型，去評估其解釋電價和股價的能力。使用實際資料來檢驗，電價資料來自歐洲電力交易市場 (EEX) 的平日現價，而股價資料則是蘋果公司 (Apple Inc.) 的歷史收盤價。在配適之前，電價資料必須先經過排除季節性因素的步驟，本文使用混合過往幾位學者的方法來表示季節性因素。經過參數估計和模擬的步驟後，我們使用三種指標檢定模擬準確度。經過實例分析後，得到均值回歸跳躍擴散模型在解釋股價上較好，而馬可夫狀態轉換模型在解釋電價上較佳的結論。然而，這個結果是否適用在世界各地其他電價市場，建議需要更多實例來驗證。

Over the past two decades, many electricity markets around the world have decided to take the path of market liberalization. Since then, both consumers as producers are exposed to significantly higher risk. And some stylized facts of electricity spot prices have been found, especially the price spike which is a behavior that the prices increase or decrease significantly and return afterwards in short time intervals. This fact enhances the difficulty for modeling. For the purpose of comparison, we also apply the historical stock closing prices which have the similar behavior, but the return rate is not as high as the stock prices.
In this paper, we use two models which include mean-reverting jump diffusion model and Markov regime-switching model to assess their ability to explain the electricity prices from the European Energy Exchange (EEX) and the stock prices from the Apple Inc. Before fitting the models, electricity prices need to be deseasonalized. After parameter estimating and simulating, we use three ways to measure the errors between the simulated values and the true values. We conclude that mean-reverting jump diffusion model is better modeling the stock prices and Markov regime-switching model has better ability to explain the electricity prices. However, if the result is the same for other market data, it suggests to further investigation.

[1] Bhanot, K., “Behavior of power prices: Implications for the valuation and hedging of financial contracts”, Journal of Risk, Vol. 2, pp. 43-62, 2000
[2] Bierbrauer, M., Tru ̈ck, S., Weron, R., “Modeling electricity prices with regime switching models” , Lecture Notes on Computer Science,Vol. 3039, pp. 859-
867, 2004
[3] Bierbrauer M. et al., “Spot and derivative pricing in the EEX power market”, Journal of Banking & Finance, Vol. 31, issue 11, pp. 3462-3485, 2007
[4] Borovkoba, S., Permana, J., “Modeling electricity prices by the potential jump-diffusion”, Stochastic Finance, 2004
[5] Cartea, A., Figueroa, M., “Pricing in electricity markets: A mean-reverting jump diffusion model with seasonality”, Applied Mathematical Finance, Vol. 12, pp. 313-335
[6] Clewlow, L., Strickland, C., “Energy Derivatives: Pricing and Risk Management”, Lacima Publications, 2000
[7] de Jong, C., “The nature of power spikes: A regime-switching approach”, ERIM Report Series ERS-2005-052-F&A, 2005
[8] Deng, S., “Stochastic models of energy commodity prices and their applications: Mean-reverting with jumps and spikes”, POWER Working Paper, PWP-073, 1999
[9] Ethier, R., Mount, T., “Estimating the volatility of spot prices in restructured electricity markets and the implications for option values”, Working paper, Cornell University, 1998
[10] Geman, H., Roncoroni, A., “A class of marked point processes for modeling electricity prices”, ESSEC Graduate Business School preprint, 2002
[11] Goldfeld, S.M., Quandt, R.M., “A Markov model for switching regressions”, Journal of Econometrics, vol. 1, pp. 3-16, 1973
[12] Haldrup, N., Nielsen, M., “A regime switching long memory model for electricity prices”, working paper 2004-2, Department of Economics, University of Aarhus
[13] Hamilton, J.D., Time Series Analysis, Princeton University Press., 1994
[14] Hamilton J.D., “A new approach to the economic analysis of nonstationary time series and business cycle”, Econometrica,Vol. 57, pp. 357-384
[15] Huisman, R., de Jong, C., “Option formulas for mean-reverting power prices with spikes”, Energy Power Risk Management, Vol. 7, pp. 12-16, 2003
[16] Huisman, R., Mahieu, R., “Regime jumps in electricity prices”, Working paper, Rotterdam School of Management, 2003
[17] Johnson, B., Barz, G., “Selecting Stochastic Processes for Modeling Electricity Prices”, Risks Books, Chapter 1, pp.3-22, 1999
[18] Knittel, C.R., Roberts, M.R., “An empirical examination of deregulated electricity prices”, POWER Working Paper, PWP-087, 2001
[19] Kosater, P., Mosler, K., “ Can Markov regime-switching models improve power- price forecasts? Evidence from German daily power prices”, Applied Energy, Vol. 83, pp. 943-958, 2006
[20] Lapuerta, C., Moselle, B., “Recommendations for the Dutch electricity market”, November 2001.
[21] Lucia, J.J., Schwartz, E., “Electricity prices and power derivatives: Evidence from the Nordic power exchange”, Review of Derivatives Research, Vol. 5, pp. 5-50
[22] Pilipovic, D., Energy Risk: Valuing and Managing Energy Derivatives,McGraw-Hill, 1997
[23] Pindyck, R., “The long-run evolution of energy prices”, The Energy Journal, Vol.20, pp. 1-27, 1999
[24] Quandt, R.E., “The estimation of parameters of linear regression system obeying two separate regimes”, Journal of the American Statistical Association, Vol. 55, pp. 873-880, 1958
[25] Shahidehpour, M., et al., Market Operations in Electric Power Systems: Forecasting, Scheduling, and Risk Management, Wiley, 2002
[26] Stevenson, M., “Filtering and forecasting spot electricity prices in the increasingly deregulated Australian electricity market”, QFRC Research Paper 63, University of Technology, Sydney, 2001
[27] Vasiček, O., J. Financial Econ., Vol. 5, 1977
[28] Weron, R., Bierbrauer, M., Tru ̈ck, S., “Modeling electricity price: Jump diffusion and regime switching”, Physica A, Vol. 336, pp.39-48, 2004
[29] Weron, R., Modeling and Forecasting Electricity Loads and Prices: A Statistical Approach, Wiley, 2006
[30] Weron, R., “Market price of risk implied by Asian-style electricity options and futures”, Energy Economics, 2007