一直以來，對如何預測的新技術的發展都是人們所感興趣的，常見的預測方法有移動平均、指數平滑以及 ARIMA 這幾種方法，但是這幾種預測方法解釋現象的能力並不強。本研究考慮應用轉換模式方法，利用二元轉換模式建構可以良好的解釋所預測時間數列起伏的因果關係。再來隨著模糊理論以及區間軟運算的技術開發，運用區間估計過程改良傳統點估計預測的不足。實際運用上更能給出較為彈性的決策空間。最後以日月光股價為例，透過轉換模式對實數值資料作模糊迴歸方法來找出模糊係數，藉此得到新的轉換模式，建構新轉換模式並與傳統轉換模式比較，探討此模式的準確性與效率性。

Stock market forecasting is an important realistic work in the financial engineering field. Generally, people use moving averages, exponential smoothing, and ARIMA to do the forecasting work. But those methods have their drawbacks, such as not efficient in the model construction or forecasting evaluation. In this research, we consider using the transfer function model to make a better and efficient forecasting work. Since the transfer function can satisfactorily explain the causation of the time series which we predicted. Moreover, with the fuzzy theories and soft computing mature, we can do an interval forecasting work for the interval time series. The proposed technique can meet the actual situation better and provided to decision-makers more flexibility of choice. In the empirical study, we can find that our model construction have a better efficient forecasting evaluation than the traditional ones. Through the transfer function to the real value data for fuzzy regression method to find the fuzzy coefficient.

吳柏林 (1995)。時間數列分析導論，華泰書局，台北。
吴柏林、林玉钧 (2002)。模糊时间数列分析与预测-以台湾地区加权股价指数为
例，应用数学学报，第 25 卷，第 1 期，页 67-76。
Khashei, M., Hejazi, S. R. and Bijari, B. (2008). A new hybrid artificial neural networks and fuzzy regression model for time series forecasting. Fuzzy Sets and Systems, 159, 769-786.

Lin, T. –S. and Yang, M. -S. (2002). Fuzzy least-squares linear regression analysis for fuzzy input-output data. Fuzzy Sets and Systems, 126, 389-399.

Manski, C. F. (1990). Nonparametric Bounds on Treatment Effects. The American Economic Review, 80(2), Papers and Proceedings of the Hundred and Second Annual Meeting of the American Economic Association, 319-323.

Nguyen, H. T. and Wu, B. (2006). Fundamemtals of Statistics with Fuzzy Data. New York：Springer.

Tanaka, H., Uejima, S. and Asai, K. (1982). Linear regression analysis with fuzzy model. IEEE Transactions on Systems, Man and Cybernetics, 12(6), 903-907.

Thomakos, D. and Guerard Jr, J. (2004). Na𝑖̈ve, ARIMA, nonparametric, transfer function and VAR models: A comparison of forecasting performance. International Journal of Forecasting, 20, 53-67.

Wu, B. and Tseng, N. -F. (2002). A new approach to fuzzy regression models with application to business cycle analysis. Fuzzy Sets and Systems, 130, 33-42.

Zadeh, L. A. (1965). Fuzzy Sets. Information and Control, 8, 338-353