:: Volume 15, Issue 2 (3-2022) ::
JSS 2022, 15(2): 443-462 Back to browse issues page
Multivariate Outlier Detection Based on Depth-Based Outlyingness Function
Sakineh Dehghan * , Mohamadreza Faridrohani
Abstract:   (3899 Views)
The concept of data depth has provided a helpful tool for nonparametric multivariate statistical inference by taking into account the geometry of the multivariate data and ordering them. Indeed, depth functions provide a natural centre-outward order of multivariate points relative to a multivariate distribution or a given sample. Since the outlingness of issues is inevitably related to data ranks, the centre-outward ordering could provide an algorithm for outlier detection. In this paper, based on the data depth concept, an affine invariant method is defined to identify outlier observations. The affine invariance property ensures that the identification of outlier points does not depend on the underlying coordinate system and measurement scales. This method is easier to implement than most other multivariate methods. Based on the simulation studies, the performance of the proposed method based on different depth functions has been studied. Finally, the described method is applied to the residential houses' financial values of some cities of Iran in 1397.
Keywords: Depth Function, Outlyingness Function, Outlier, Affine Invariance.
Full-Text [PDF 727 kb]   (1398 Downloads)    
Type of Study: Applied | Subject: Statistical Inference
Received: 2021/02/26 | Accepted: 2022/03/1 | Published: 2021/10/4



XML   Persian Abstract   Print



Rights and permissions
Creative Commons License This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Volume 15, Issue 2 (3-2022) Back to browse issues page