Outlier identification in high dimensions

By Peter Filzmoser, Ricardo A. Maronna, Mark Werner. Computational Statistics & Data Analysis, 2008

439 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Molecular Biology, Statistics and Probability

View Paper: https://www.semanticscholar.org/paper/af6238a1c6ae858337bb382bdf9dacffd383fc50

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Molecular Biology

In Statistics and Probability

Citations in the corpus

Heartbeat Classification Using Feature Selection Driven by Database Generalization Criteria (2011, methodology): “Then, in a second phase, the directions of large variance are explored to address scatter outliers [ 21 ].”
Generalized Measures of Correlation for Asymmetry, Nonlinearity, and Beyond (2012, methodology): “…the sample size fixed at n = 60, we evaluate the coverage rates based on 1000 replications in two ways: one with the outliers in the sample, and another one with the outliers being “removed” using the outlier removal function in the R package “mvoutlier” (see Filzmoser, Maronna, and Werner 2008).”
HiCS: High Contrast Subspaces for Density-Based Outlier Ranking (2012, methodology): “Given the notion of probability density in any subspace S, we measure the contrast by comparing conditional probability densities to the corresponding marginal densities for all attributes si ∈ S.”
Invariant co‐ordinate selection (2009, methodology): “Here I used an outlier detection method that is not affine equivariant (Filzmoser et al, 2008) and, although theoretical results for ICS would no longer hold, the practical results are very useful.”
Principal Component Analysis on Spatial Data: An Overview (2013, neutral): “Many robust PCA techniques are computationally intensive and, as such, computationally fast algorithms are required for analyzing large high-dimensional data sets (eg, see Filzmoser, Maronna, and Werner 2008 ).”
Contextual Outlier Interpretation (2017, background): “Some other work tackles the curse of dimensionality [Filzmoser et al., 2008], the massive data volumn [Ramaswamy et al.”
Equivariance and invariance properties of multivariate quantile and related functions, and the role of standardisation (2010, background): “The relation (17) has independent interest and indicates a significant further property of M0(·) that we discuss in Section 6.”
Bootstrap based confidence limits in principal component analysis: a case study (2013, background): “One way to handle the negative effects of the outliers is to attempt and detect plus remove them [1,36] from the empirical data simultaneously with pre-processing and initial data inspection.”
Rainbow Plots, Bagplots, and Boxplots for Functional Data (2010, methodology): “Another multivariate outlier detection method is the location-scale approach of Filzmoser et al. (2008).”