English  |  正體中文  |  简体中文  |  Items with full text/Total items : 27005/38806
Visitors : 2402401      Online Users : 76
RC Version 4.0 © Powered By DSPACE, MIT. Enhanced by NTU Library IR team.
Scope Adv. Search

Please use this identifier to cite or link to this item: http://ntour.ntou.edu.tw:8080/ir/handle/987654321/13004

Title: 共線性下投資函數的分析比較
The Comparison of Different Investment Models Under Multicollinearity
Authors: Sheng-Yao Huang
Contributors: NTOU:Institute of Applied Economics
Keywords: 投資函數;逐步迴歸;主成份分析法;脊迴歸分析法
investment function;stepwise regression;principal component;ridge regression
Date: 2005
Issue Date: 2011-06-30T07:09:29Z
Abstract: 本論文使用三種不同的計量方法,檢視民間固定資本形成毛額的因素,並加以比較分析。實證策略上,首先運用一般加速理論、現金流量理論、新古典投資理論和證券價值等四大經濟理論,從中選擇影響投資函數的38個總體經濟變數。其次,再分別以逐步迴歸分析法、主成份分析法及脊迴歸分析法進行分析,最後對於分析出的結果進行比較。研究資料的型態以靜態資料為樣本,期間自1976年第1季至2004年第4季的總體經濟資料,做為研究基礎。 進行實證分析之前,先將資料做單根檢定,發現資料呈現不穩定現象,因此我們將資料進行差分處理,並將資料區分成水準值和差分值,再分別以不同計量方法分析。我們發現:主成份分析法及脊迴歸分析法,會因為變數資料之間的相關性很高,皆出現不穩定的現象,效果不如預期。 最後,採逐步迴歸法分析法再配合落遲性的概念後,結果得到很高的判定係數及很小的尾端機率,證明經濟理論的概念是有效的而且導出的模型的效果顯然比主成份分析法及脊迴歸分析法為佳。 關鍵字:投資函數、逐步迴歸法、主成份分析法、脊迴歸分析法。
In this thesis, the investment related series are under investigation. We use three econometric methods in our study. We apply stepwise regression method combined with big four theories about making decision for investment behavior. The four theories are generalized accelerator, cash flow, neoclassical and securities valuation. In total, we choose 38 items of variables from investment function. And then we use the tool of multiple regression to proceed all the analysis. After that we compare it with results of principal component and ridge regression. All the data are from AREMOS data bank. The sample period ranges from the first quarter in 1976 through the fourth quarter in 2004 . In the first step, we consider the unit root test to check the stationarity in the data. The finding is that variables in the set are nonstationary in general. However we have done the work both in the differenced form and in the level form. For the former solution, we follow the tradition procedure suggestion to take difference prior to the analysis. For the latter one, we adopt the theory under the framework of cointegration regression. Judging from all the results, we have found stepwise regression method under the guidance of economic theories performs best. And the outcomes from principal component and ridge regression are not reliable if the data range wide and normalization is not applied. We hope this result is good for all the private agencies and organizations in the government. Key words: investment function, stepwise regression, principal component, ridge regression.
URI: http://ethesys.lib.ntou.edu.tw/cdrfb3/record/#G0M93350013
Appears in Collections:[應用經濟研究所] 博碩士論文

Files in This Item:

File Description SizeFormat

All items in NTOUR are protected by copyright, with all rights reserved.


著作權政策宣告: 本網站之內容為國立臺灣海洋大學所收錄之機構典藏,無償提供學術研究與公眾教育等公益性使用,請合理使用本網站之內容,以尊重著作權人之權益。
網站維護: 海大圖資處 圖書系統組
DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - Feedback