Data perturbation analysis of a linear model

来源期刊：中国有色金属学报(英文版)2000年第2期

论文作者：靳奉祥 Michel Mayoud 卢秀山 Jean-Pierre Quesnel

文章页码：280 - 283

Key words：linear model; data perturbation; mean shift perturbation

Abstract: The linear model features were carefully studied in the cases of data perturbation and mean shift perturbation. Some important features were also proved mathematically. The results show that the mean shift perturbation is equivalent to the data perturbation, that is, adding a parameter to an observation equation means that this set of data is deleted from the data set. The estimate of this parameter is its predicted residual in fact.