English  |  正體中文  |  简体中文  |  全文筆數/總筆數 : 6507/11669
造訪人次 : 30036221      線上人數 : 550
RC Version 3.2 © Powered By DSPACE, MIT. Enhanced by NTU Library IR team.
搜尋範圍 進階搜尋

請使用永久網址來引用或連結此文件: http://ir.ncue.edu.tw/ir/handle/987654321/13348

題名: 週期性異常現象之再檢視---台灣產業別之觀察
A Further Examination of Calendar Anomalies---An Observation of Industry Groups in Taiwan
作者: 林哲鵬
貢獻者: 企業管理學系
關鍵詞: 週期性異常現象;年度效應;星期效應;假日效應;台灣;股票市場;Calendar anomaly;Turn-of-the-year effect;Day-of-the-week effect;Holiday effect;Taiwan;Stock market
日期: 1997-08
上傳時間: 2012-08-13T02:08:50Z
出版者: 行政院國家科學委員會
摘要: 由於過去文獻提及產業效應之存在,本計劃旨在以產業分類為基礎,進一部觀察台灣股市週期性異常現象之健全性。檢驗方法包括虛擬變數迴歸模型以及健全性測試。研究中,將先以虛擬變數迴歸模型,檢視台灣各產業類股是否存有潛在之週期性異常現象,再以健全性試驗,檢查資料經過大樣本數的調整和殘值誤差調整之後,此等異常現象在統計上是否依然顯著。近來研究指出,過去所發現之週期性異常現象,大多是基於傳統迴歸模型下所觀察之結果。若將此模型給予健全性檢視,並加以調整,其實大多週期性異常現象多已不復存在。不過,研究仍多以整體市場為著眼點,少有產業分類後之深入分析;而產業因素在過去文獻中,亦被指出對股價報酬變化有顯著之解釋能力。因此,本計劃連結上述相關思考,期予此研究領域進一步之闡釋。
Previous literature points out that industrial structure plays an important role in describing the stock price behavior. After classifying various industry groups, this study reexamines the day-of-the-week effect in Taiwan for the period between January 6, 1987 and October 2, 1997. Methodologies include ARCH/GARCH type and Bayesian-t large sample size corrections on OLS regression models. It is observed that with appropriate error term and large sample size adjustments, the potential day-of-the-week effect for the market disappeared, while abnormal positive
Saturday returns remain statistically significant among some industry groups. Evidence in this study suggests that industry classification is an important factor for studying the day-of-the-week effect. The price behavior based on the aggregate market and industry groups both provide valuable information for portfolio manager‘s investment decisions.
關聯: 國科會計畫; 計畫編號:NSC87-2415-H035-015; 研究期間:86/08-87/07
顯示於類別:[企業管理學系] 國科會計畫

文件中的檔案:

檔案 大小格式瀏覽次數
2060200712001.pdf187KbAdobe PDF384檢視/開啟


在NCUEIR中所有的資料項目都受到原著作權保護.

 


DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - 回饋