臺灣博碩士論文加值系統

本文主要討論迴歸樹方法對資料預測能力的差異.我們使用PARTY與GUIDE兩種迴歸樹狀方法,藉由不同的擬合方式,透過51筆實際資料來暸解並比較其預測能力的優劣.平均而言,以GUIDE方法在Stepwise-fit與Linear-fit上預測能力表現最好,PARTY的Constant-fit方法最差.

1.導論 1
2.迴歸樹方法的介紹 3
2.1 GUIDE方法...........................4
2.2 PARTY方法...........................5
3.預測能力的比較 6
3.1 資料集..............................6
3.2 實驗設計............................6
3.3 實驗結果分析.......................10
4.結論 14
5.附錄 15
5.1 原始資料一.........................16
5.2 原始資料二.........................17

[1] Breiman, L., Friedman, J. H., Olshen, R. A. and Stone, C. J.(1984).
Classification and Regression Trees,Wadsworth, Belmont.
[2] Hothorn, T., and Hornik, K. and Zeileis, A.(2006).
Unbiased Recursive Partitioning: A Conditional Inference Framework
Journal of Computational and Graphical Statistics, 15(3): 651-674.
[3] Kim, H., and Loh, W.-Y. and Shih, Y.-S. and Chaudhuri, P.(2007).
Visualizable and Interpretable Regression Models With Good Prediction Power,
IIE Transactions, 39: 565-579.
[4] Loh, W.-Y.(2002).
Regression trees with unbiased variable selection and interaction detection,
Statistica Sinica,12(2): 361-386.
[5] Simonoff, J. S.} (2003). {em Analyzing Categorical Data, Springer, Berlin.
[6] Strasser, H., and Weber, C.(1999).
On the Asymptotic Theory of Permutation Statistics,Mathematical Methods of Statistics, 8, 220-250.