透過您的圖書館登入
IP:3.17.6.75
  • 期刊

亞洲金融危機後台灣出口貿易之動態分析-時間數列模式之應用

The Impact of Asian Financial Crisis on the Dynamic Processes of Taiwan's Exports-An Application of Time Series Models

摘要


本研究目的是針對傳統時間數列模式與模糊時間數列之二因子模式、引導式模式及馬可夫模式預測方法在應用上之比較,並以台灣出口金額之預測為例。由本文實證結果發現,模糊時間數列模式在研究期間較短時有較佳的預測能力,其中以引導式模式之操作方法最為簡易,預測結果相對較佳,而時間數列ARIMA模式在較長的研究期間其預測誤差(MSE)較小。所以就預測的普遍性、實用性和急迫性的考量下,模糊時間數列模式可以迅速提供簡捷的訊息給決策者。

並列摘要


This study compares the forecasting methods of ARIMA time series and fuzzy time series by Two-factor models, Heuristic models, and Markov models based on the amount of Taiwan export. It is found that the methods of fuzzy time series models behave better in forecasting ability than that of ARIMA time series model for a short period, namely their mean square error (MSE) is smaller. The Heuristic model is the easiest method to follow. For account of popularity, practicality and urgency, the methods of fuzzy time series models are good choices.

延伸閱讀