The cross-validation (CV) method proposed by Allen (1974) and
Stone (1974) has been widely used for the model selection of
linear and nonparametric regression models. It isessentially a
method based on the idea of the delete-1 jackknife.
Shao (1993) proposed the high order CV method (CVnv) to rectify
the deficiency of CV in linear model selection. In this study,
we suggest using CVnv for the model selection of nonparametric
additive models. The results from simulation study are
presented.

目 錄
1 研究介紹
2 非參數迴歸模型之估計與交叉驗證技術
2.1 平滑技術
2.1.1 核密度估計
2.1.2 lambda-最近鄰域估計
2.1.3 雲狀平滑
2.2 非參數迴歸模型
2.2.1 非參數迴歸模型之介紹
2.2.2 可加性模型
2.3 交叉驗證選模準則
2.3.1 參數線性模型之選模準則與交叉驗證
2.3.2 非參數模型選模準則與交叉驗證技術
3 可加性模型下之交叉驗證技術
3.1 介 紹
3.2 高階交叉驗證技術
3.3 高階交叉驗證之計算方法
4 模 擬
4.1 模擬介紹
4.1.1 單變量平滑者之模型與資料生成
4.1.2 可加性模型與資料生成
4.2 模擬結果與比較
4.2.1 單變量立方平滑雲狀模擬結果與比較
4.2.2 單變量局部加權移動線平滑模擬結果與比較
4.2.3 可加性模型模擬結果與比較
5 結論備註
附 錄
參考文獻

Akaike, H. (1969). "Statistical predictor identification,"
Ann. Inst. Statist. Math., 22, 203-217.
Allen, D. M. (1974). "The relationship between variable
selection and data augmentation and a method for prediction,"
Technometrics, 16, 125-127.
Shao, J. (1993). "Linear model selection by cross-
validation," JASA., 88, 486-494.
...