摘要
研究多元非参数模型曲线族 ,对每一条曲线建立一个多元非参数回归方程 ,许多形状相似的曲线借助于参数与一条参考曲线联结成一个曲线族 ,研究了如何综合使用多元核函数、投影寻踪回归。
Each curve belongs to a multivariate nonparametric regression model, and many shape invariant curves form a curve family connected with a reference curve by some parameters. The fitting methods in the curve family, by using multivariate kernel function, projection pursuit regression, self modeling regression under the condition of shape invariant and cross validation technology, are investigated. Some methods of the curve drift in different circumstances are described.
