Outliers are minority observations do not conform to the model suggested by the homogeneous majority of the observations Outliers causes lost of the information supported by the majority of the observations Many approach are exist for determination of outliers The choice of appropriate test is depend on the distribution of the data the distribution of parameters and the type or and the number of the outliers that expected In this study we proposed a new method for determining of outliers in low and high dimensional data depend on clustering The effectiveness of the method is shown on real and simulated data sets Key Words: Clustering Detecting of Outlier High Dimensional Data
Benzer Makaleler | Yazar | # |
---|
Makale | Yazar | # |
---|