I applies Quasi Maximum Likelihood method to estimate the parameters of SV model,illustrates how to identify the influential point of the data on the basis of the minor perturbation of the model,simulates a SV model and identifies influential points t.

The influential point test for the linear model and the generalized linear model are discussed.

In the past years,the classification of the differences between the jump point and the strong influential point has aroused people s attention,because it has great significance for the estimation of parameter, model,etc.

With the wide application of data mining to modern business, the researches of data mining for outlier and influential point have been paid close attention to by economic and statistical circles.

The least absolute criteria with better robustness should be adopted for parameter estimation when there are outliers or influence cases in the data.