https://scholars.lib.ntu.edu.tw/handle/123456789/81916
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor | 陳正剛 | en |
dc.contributor | 臺灣大學:工業工程學研究所 | zh_TW |
dc.contributor.author | 黃奕禧 | zh |
dc.contributor.author | Huang, Yi-Hsi | en |
dc.creator | 黃奕禧 | zh |
dc.creator | Huang, Yi-Hsi | en |
dc.date | 2005 | en |
dc.date.accessioned | 2007-11-26T01:06:45Z | - |
dc.date.accessioned | 2018-06-29T00:33:29Z | - |
dc.date.available | 2007-11-26T01:06:45Z | - |
dc.date.available | 2018-06-29T00:33:29Z | - |
dc.date.issued | 2005 | - |
dc.identifier | en-US | en |
dc.identifier.uri | http://ntur.lib.ntu.edu.tw//handle/246246/51205 | - |
dc.description.abstract | 迴歸樹 (Regression Trees) 可以用來處理類別性或是連續性的response,但是迴歸樹在選擇變數 (attributes) 時,持續對資料做分割會造成樣本數迅速減少而造成不可靠的估計。提高樣本使用率之迴歸樹 (Sample-Efficient Regression Trees) 即是用來處理迴歸樹樣本數急速減少的問題。然而,當資料有著continuous effects,variant continuous effects,以及mixed effects時,迴歸樹以及提高樣本使用率之迴歸樹均無法處理這些問題。 在處理continuous effects時,我們結合了逐步迴歸分析以及提高樣本使用率之迴歸樹的方法來解決這個問題。針對variant continuous effects,我們提出了一種同時考量一個變數的continuous effects以及discrete effects的變數選擇方法來處理這個問題。最後,在處理mixed effects時,我們除了考量一個變數單一的影響外,此變數下一層選出來的變數對於整個model的解釋能力的影響也會被考慮。 為了驗證我們提出的方法,我們利用一些模擬所產生的資料以及一個關於體脂肪的實際案例,對於我們提出的方法以及一些其他的方法做比較。經過一些比較分析的結果,證明了新提出的方法可以有效的解決continuous effects ,variant continuous effects,以及mixed effects。 | zh_TW |
dc.description.abstract | Classification and regression trees (CART) is a type of decision-tree techniques, used to deal with either categorical or continuous response. A shortcoming of the regression tree is that the splitting procedure exhausts the sample size quickly. Sample-Efficient Regression Trees (SERT) is developed to address the sample-size-depleting issue. However, both SERT and CART are only able to select the attributes with discrete effects. The attributes with continuous effects, variant continuous effects, and mixed effects will not be selected into the tree model by CART and SERT. In this research, we integrate the stepwise regression method and sample-efficient regression tree approach to select attributes with continuous effects. When dealing with attributes with variant continuous effects, we propose a method to consider simultaneously the continuous effect and discrete effect of an attribute. For the attributes with mixed effects, we consider not only the effect of attribute but also that of the attributes selected subsequently. In order to validate the methods we proposed, we test the proposed tree using some simulated data with continuous effects, variant effects, and mixed effects. A real case about the body density of 252 men is also studied. With the validation of the simulated data and the real case, we verify that the new decision tree is able to select attributes that other decision trees fail to select and build a more robust tree model with attributes effects more accurately estimated. | en |
dc.description.tableofcontents | Abstract i 中文摘要 ii Contents iii Contents of Figures v Contents of Tables vii Chapter 1 Introduction 1 1.1 Backgrounds 1 1.2 Motivation and Problem Description 6 1.3 Thesis Organization 9 Chapter 2 A Piecewise-Linear Regression Tree 10 2.1 Selection of Attributes with Discrete and Continuous Effects 10 2.2 Selection of Attributes with Variant Continuous Effects 18 2.3 Selection of Attributes with Mixed Effects 23 2.4 Selection of Attribute Combinations 25 2.5 The Stopping Criterion 29 2.6 The Complete Procedure 31 Chapter 3 Case Study 33 3.1 Simulated Cases 33 3.1.1 Scenario 1: The Attributes with Continuous Effects 33 3.1.2 Scenario 2: The Attributes with Variant Continuous Effects 35 3.1.3 Scenario 3: The Attributes with Mixed Effects 38 3.1.4 Scenario 4: The Attribute Combination 43 3.2 A Real Case 46 Chapter 4 Conclusions 49 Reference 50 Appendix 51 A. The main class of Piecewise-Linear Regression Trees 51 B. The class diagram of the Piecewise-Linear Regression Trees system 52 | zh_TW |
dc.format.extent | 652900 bytes | - |
dc.format.mimetype | application/pdf | - |
dc.language | en-US | en |
dc.language.iso | en_US | - |
dc.subject | 迴歸樹 | en |
dc.subject | 提高樣本使用率之迴歸樹 | zh_TW |
dc.subject | regression trees | en |
dc.subject | Sample-Efficient Regression Trees | en |
dc.title | 逐段線性迴歸樹 | zh |
dc.title | Sample-Efficient Regression Trees for Attributes with Mixed Continuous and Discrete Effects-A Piecewise-Linear Regression Tree | en |
dc.type | thesis | en |
dc.identifier.uri.fulltext | http://ntur.lib.ntu.edu.tw/bitstream/246246/51205/1/ntu-94-R92546018-1.pdf | - |
dc.relation.reference | [1] J. Han and M. Kamber., Data Mining Concepts and Techniques. Morgan Kaufmann publisher, 2001. [2] L. Breiman, J. H. Friedman, R. A. Olshen, and C. J. Stone, Classification and Regression Trees. Monterey, CA: Wadsworth, 1984. [3] T. R. Ho, “Sample-Efficient Regression Tree for Binary and Ordinal Attributes and Continuous Target”, M.S. Thesis, Graduate Institute of Industrial Engineering, National Taiwan University, National Taiwan University, 2003. [4] C. W. Liu, “Enhanced Sample-Efficient Regression Trees with MaxF Selection Criterion and Attribute Combination Selection”, M.S. Thesis, Graduate Institute of Industrial Engineering, National Taiwan University, National Taiwan University, 2004. [5] J. Jaccard, R. Turrisi, and K. W. Choi, Interaction Effects in Multiple Regression, SAGE publications, 1990. [6] L. S. Aliken and S. G.. West, Multiple Regression: Testing and Intercepting Interactions, SAGE publications, 1991. [7] P. D. Allison, “Testing for Interaction in Multiple Regression”, The American Journal of Sociology, vol. 83, no. 1, pp. 144-153. [8] C. L. Lin, “Robust Test for batch-and-batch variable selection”, M.S. Thesis, Graduate Institute of Industrial Engineering, National Taiwan University, National Taiwan University, 2004. [9] R. B. Bendel and A. A. Afifi, “Comparison of stopping rules in forward stepwise regression”, Journal of American Statistical Association, vol. 72, pp. 46-53, 1997. | en |
item.openairecristype | http://purl.org/coar/resource_type/c_46ec | - |
item.openairetype | thesis | - |
item.languageiso639-1 | en_US | - |
item.grantfulltext | open | - |
item.cerifentitytype | Publications | - |
item.fulltext | with fulltext | - |
顯示於: | 工業工程學研究所 |
檔案 | 描述 | 大小 | 格式 | |
---|---|---|---|---|
ntu-94-R92546018-1.pdf | 23.53 kB | Adobe PDF | 檢視/開啟 |
在 IR 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。