The Mahalanobis distance

By R. Maesschalck, D. Jouan-Rimbaud, D. Massart. 2000

1,371 citations recorded by the source corpus.

Subfields: Analytical Chemistry, Control and Systems Engineering, Statistics and Probability

View Paper: https://www.semanticscholar.org/paper/31d17543f3051d32a767b84c25c6efbbdbb5e94f

How researchers see this paper

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

In Analytical Chemistry

1. João Gama
2. Beata Walczak
3. Krzysztof Kaczmarek
4. M. R.
5. A. R.
6. LARKb
7. Viscarra ROSSELa
8. Michael Daszykowski

In Control and Systems Engineering

1. João Gama
2. Yongjun Hong
3. Sungroh Yoon
4. Heather Berry
5. Mauro F. Guillén
6. Nan Zhou

In Statistics and Probability

1. André Carlos Ponce de Leon Ferreira de Carvalho
2. Rodrigo C. Barros
3. João Gama
4. Beata Walczak
5. Eduardo R. Hruschka
6. Elaine Ribeiro de Faria
7. Krzysztof Kaczmarek
8. Jonathan de Andrade Silva

Citations in the corpus

• Robust statistics in data analysis — A review: Basic concepts (2007, methodology): “To overcome this problem, the original data variables can be replaced by orthogonal principal components [35].”
• An institutional approach to cross-national distance (2010, methodology): “Scholars familiar with principal-component analysis will realize that the Mahalanobis distance is equivalent to the Euclidean distance calculated with the standardized values of the principal components (De Maesschalck et al., 2000).”
• Improved analysis and modelling of soil diffuse reflectance spectra using wavelets (2009, methodology): “Outlier detection was conducted using theMahalonobis distance statis- tic (De Maesschalck et al., 2000) on the scores of the first five PLS factors.”
• Data stream clustering: A survey (2013, methodology): “Therefore, for every remaining object x , PDC2 finds its closest centroid according to the Mahalanobis distance [Maesschalck et al. 2000], say the centroid of cluster Ci; afterwards, the centroid of Ci is perturbed and moved the farthest away from x (within a pre-calculated confidence interval).”
• How Generative Adversarial Networks and Their Variants Work (2017, background): “dtheembeddingdirectionvwhichmaximizesthe meandiscrepancywhileconstrainingittolieinahyperellipsoidasvT(1 2 P w (p data)+ 1 2 P (p g)+ I m)v= 1 represents. It naturally derives the Mahalanobis distance [21] which is defined as a distancebetweentwodistributionsgivenapositivedefinitematrixsuchasacovarianc”