| 研究生: |
郭子文 |
|---|---|
| 論文名稱: |
財務時間序列中非線性特質的Agent-Based 基礎 : 遺傳規劃的應用 |
| 指導教授: | 陳樹衡 |
| 學位類別: |
碩士
Master |
| 系所名稱: |
社會科學學院 - 經濟學系 Department of Economics |
| 論文出版年: | 1998 |
| 畢業學年度: | 87 |
| 語文別: | 中文 |
| 論文頁數: | 105 |
| 相關次數: | 點閱:160 下載:0 |
| 分享至: |
| 查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報 |
本論文先以Pagan(1996)所整理的實證結果為代表,對實際金融市場資料常具有的典型特質及其相關的檢定作介紹;接著嘗試建構一個簡單的經濟模型,在沒有很多的外生條件設定下,由模型內生的產生實際金融市場資料常具有的典型特質,本文應用Koza(1992)所發展的遺傳規劃(Genetic Programming)為工具,建立一個具有異質性、調適性的多決策者模型架構,模擬一個含生產者與投機者的人工市場,讓生產者、投機者的行為內生決定,並利用計量檢定分析此市場具有哪些實際市場常見的典型特質,並探討這些特質和經濟制度之間的關聯性。
第一章 緒論..........1
第二章 文獻回顧..........5
2.1 簡要說明..........5
2.1.1 關於Agent-Based之說明
2.1.2 關於所列文章之說明
2.2 Lux(1996、1997)、Tayler(1995)和Arthur(1996)文章..........6
2.3 Lux、Tayler、Arthur文章與本論文的比較..........13
第三章 模型建構..........15
第四章 遺傳規劃的學習..........18
4.1 簡介..........18
4.2 遺傳規劃的設計與運作..........19
4.3 模擬結果的簡單敘述統計..........21
4.4 演化至9000代時,Tree平均的結點數和深度..........24
第五章 模擬結果的統計檢定分析..........33
5.1檢定進行步驟..........33
5.2檢定概述及有關設定..........35
5.3檢定結果分析..........40
第六章 結論與未來研究方向..........45
附錄 表格..........46
參考文獻..........95
[1] 張維娟(1 997) ,投機者的學習過程與其經濟效果:遺傳規劃在多決策者模型
上的應用,國立政治大學經濟研究所碩士論文。
[2] Arthur W. B, J. H. Holland, B. LeBaron, R. Palmer, and P. Tayler (1 996),“Asset
Pricing Under Endogenous Expectations in an Artificial Stock Market," Santa Fe
Institute SSRl Working Paper #9625 .
[3] Barnet, William A., A. Ronald Gallant, Melvin J. Hinich, Jochen A. Jungeilges,
Daniel T. KapJan, and Mark 1. Jensen (1996),“A Single-Blind Controlled
Competition Among Tests for Nonlinearity and Chaos", Working Paper
[4] Bollerslev, T. (1 986),“Generalized Autoregressive Conditional Heteroskedasticity,"
Journal of Econometrics, Vol 31, pp.307-327
[5] Brock, W. A., W. D. Dechert, B. LeBaron, and J. Scheinkman (1996), "A Test for
Independence Based on the Correlation Dimension", Ecol1omelric Reviews 15 ,
pp.197-235.
[6] Brock, W. A., D. A. Hsieh, and Blake LeBaron (1 991), Nonlinear Dynαnucs,
Chaos, and lnstability : Statistical TheOly ω/d Economic Evidence, Cambridge,
MA.: M.I.T Press.
[7] Chen, S.-H. and C. -H. Yeh (1 997), “Modelling Speculators with Genetic Programming",forthcoming in Evolutionary Programming VI, Springer-Verlag
[8] Chen, S.-H. and C.-H. Yeh (1 997), “ Speculative Trades and Financial Regulations:
Simulations Based on Genetic Programming", A11I7lIal Conference 011
Computationallnte/ligenGe for Finoncial Engil7eering (CIFER'97)
[9] De Lima, P. F. (1998), "Nonlinearities and Nonstationarities in Stock Returns竹,
American Statistical Associatiol7 Joumal of BusiJ/ess & EcoJ7omic SIαtistics, Vol
16. No. 2
[10] Kaplan, Daniel T. (1 994), “ Exceptional Events as Evidence for Determinism",
Physicα D 73 , pp.38-48
[11] Koza, J. R. (1992), Genetic Pl'Ogmmming: 0n the Progmmming of Complltel's
by Means of Natuml Selectiol7, M. I.T Press
[12] Koza, J. R. (1 994), Genetic Pl'Ogmmming 11 ,Chapter 2. M.I.T Press.
[13] Kwiatowski, D., P. C.B. Phillips, P. Schmidt and Y. Shin (1992),“Testing the
Null Hypothesis of Stationarity agaínst the Alternatíve of A Unít Root'\ Journalof
Econometrics 54, pp.159-178 .
[14] Lux, T. (1996),“The Socío-Economíc Dynamics of Speclllative Markets
Interactíng Agents, Chaos, and the Fat Tails ofReturn Distributions," forthcoming
ín Joumal of Economic Be J(l' and Ol'gα, nizα110n.
[15] Lux, T. (1 997) ,”Vlatility Clustering in Financial Markets: A Micro-Símulation
of Interactive Agents," Technicα1 Repol't, Department ofEconomlcs, University of
Bamberg, Germany.
[16] Muth, J. F. (1 961),“Rational Expectations and the Theory of Príce Movements",
Ecol1ometrica 29, pp.315-33 5.
[17] Pagan, A. (1996),“The Econometrics ofFinancial Markets," Journal of
Enψirical Finance 3, pp.15-1 02.
[18] Tayler, P. (1 995),“Modelling Artificial Stocks Markets lIsing Genetic
Algoríthms," in S. Goonatilake and P. Treleaven (eds.), lntelligent Systemsfor
Finαnce and Business, pp.271-288.
[19]Tsay, R., (1986),“Nonlinearity Tests for Time Series", Biometrika 73} 461-466.
(限達賢圖書館四樓資訊教室A單機使用)