Robust statistics for outlier detection
โ Scribed by Peter J. Rousseeuw; Mia Hubert
- Book ID
- 112233019
- Publisher
- Wiley (John Wiley & Sons)
- Year
- 2011
- Tongue
- English
- Weight
- 150 KB
- Volume
- 1
- Category
- Article
- ISSN
- 1942-4787
- DOI
- 10.1002/widm.2
No coin nor oath required. For personal study only.
๐ SIMILAR VOLUMES
The sum of least-squares regression method is normally used when principal components are extracted from a data matrix. This may result in a misleading set of principal components if outliers are present in the data set, in terms of both the number of components and their direction in vector space.
In this paper we suggest a simple way of constructing a bivariate boxplot based on convex hull peeling and B-spline smoothing. The proposed method shows some advantages with respect to that suggested by Goldberg and Iglewicz (1992). Our approach leads to defining a natural inner region which is comp