Title: 應用景氣對策信號指標建構台灣股市大盤加權指數多變量時間序列預測模型
Constructing a Multivariate Time-Series Prediction Model for Weighted Index of Taiwanese Stock Market using Business Monitoring Indicators
Authors: 吳駿
唐麗英
管理學院工業工程與管理學程
Keywords: 多變量時間序列;景氣對策信號;股市預測模型;Multivariate time series;Business monitoring indicators;Prediction model of stock
Issue Date: 2012
Abstract: 現今萬物均大幅上漲,而薪水增加的速度卻遠比不上食物類等民生必需品價 格上漲的幅度。面對實質薪資呈現負成長的時代,利用投資來增加收入已是全民課題。面對眾多的投資商品,在報酬與風險權宜之下,投資金額彈性大但可獲取相對高報酬的股市即成為投資大眾的最愛。台灣股市大盤加權指數的波動比個股相對要小,表示投資台灣股市大盤加權指數的商品風險較小(例如:台灣50指數型基金),為了要降低投資風險,股票投資者需要ㄧ個有效之股市大盤加權指數預測模型作為投資之參考。因此,本研究之主要目的是利用景氣對策信號之構成元素來建立一個台灣股市大盤加權指數之多變量時間序列預測模型,以預測加權指數之走勢及分析景氣對策信號各構成元素對台灣股市大盤加權指數的影響。本研究以1999年1月至2012年5月之景氣對策信號指標與台灣股市大盤加權指數資料為實例,驗證了本研究方法確實有效。本研究之實例分析結果顯示:1、台灣股市大盤加權指數之時間序列模型有落後期不連續的情形,表示台灣股市大盤加權指數僅受特定落後期之歷史資料影響;2、景氣對策信號之八項指標(不含股價指數)中僅貨幣總計數(M1B)對於時間序列預測模型有顯著之正向影響。
In recent years,price increases sharply for almost everything,except salary increase. To deal with the negative growth of salary,investment is a universal issue. Among many investment,stock market is flexible and may gain a relatively high return. Thus,it becomes a favorite investment. The main purpose of this study is to establish a prediction model for the weighted index of Taiwanese stock market using multivariate time series and business monitoring indicators. This study collected data of business monitoring indicators from January 1999 to May 2012 along with the weighted index of the Taiwanese stock market to demonstrate the effectiveness of the proposed method. The results indicate that:1.The weighted index of Taiwanese stock market is affected only by specific lagged historical data;2.Among eight business monitoring indicators (excluding stock index),only monetary aggregates M1B has significant positive impact on the predictive model.
URI: http://140.113.39.130/cdrfb3/record/nctu/#GT079963502
http://hdl.handle.net/11536/50725
Appears in Collections:Thesis