It is necessary to make a reasonable covariance structure for longitudinal data so as to fit these data with linear or nonlinear models.
为了用线性或非线性模型拟合纵向数据，需要确定一个合理的协方差结构。
2
The results of PCA and DPC show that the sampling data have a remarkable nonlinearstructure.
PCA和DPC分析结果表明，取样数据具有明显的非线性结构。
3
In this paper, the principle of nonlinear correction of data by using RBF neural network, the structure of neural network and the determination method of parameters are described.