The Mahalanobis distance is a measure of the distance between a point and a distribution , introduced by P. C. Mahalanobis in 1936.[1] The mathematical details of Mahalanobis distance has appeared in the Journal of The Asiatic Society of Bengal.[2] Mahalanobis's definition was prompted by the problem of identifying the similarities of skulls based on measurements (the earliest work related to similarities of skulls are from 1922 and another later work is from 1927).[3][4] The sampling distribution of Mahalanobis distance has been obtained by Professor R.C. Bose, under the assumption of equal dispersion.[5]
It is a multivariate generalization of the square of the standard score : how many standard deviations away is from the mean of . This distance is zero for at the mean of and grows as moves away from the mean along each principal component axis. If each of these axes is re-scaled to have unit variance, then the Mahalanobis distance corresponds to standard Euclidean distance in the transformed space. The Mahalanobis distance is thus unitless, scale-invariant, and takes into account the correlations of the data set.
^"Reprint of: Mahalanobis, P.C. (1936) "On the Generalised Distance in Statistics."". Sankhya A. 80 (1): 1–7. 2018-12-01. doi:10.1007/s13171-019-00164-5. ISSN 0976-8378.
^Journal and Procedings Of The Asiatic Society Of Bengal Vol-xxvi. Asiatic Society Of Bengal Calcutta. 1933.
^Mahalanobis, Prasanta Chandra (1922). Anthropological Observations on the Anglo-Indians of Culcutta---Analysis of Male Stature.
^Mahalanobis, Prasanta Chandra (1927). "Analysis of race mixture in Bengal". Journal and Proceedings of the Asiatic Society of Bengal. 23: 301–333.
^Science And Culture (1935-36) Vol. 1. Indian Science News Association. 1935. pp. 205–206.
and 26 Related for: Mahalanobis distance information
Mahalanobis in 1936. The mathematical details of Mahalanobisdistance has appeared in the Journal of The Asiatic Society of Bengal. Mahalanobis's definition...
Chandra Mahalanobis OBE, FNA, FASc, FRS (29 June 1893– 28 June 1972) was an Indian scientist and statistician. He is best remembered for the Mahalanobis distance...
to a multiplicative factor, the squared Mahalanobisdistance is a special case of the Bhattacharyya distance when the two classes are normally distributed...
distance) to be used for linear inverse problems in inference by optimization theory. Other important statistical distances include the Mahalanobis distance...
also known as the Kantorovich metric, or earth mover's distanceMahalanobisdistance Amari distance Integral probability metrics generalize several metrics...
}}^{-1}({\mathbf {x} }-{\boldsymbol {\mu }})}}} is known as the Mahalanobisdistance, which represents the distance of the test point x {\displaystyle {\mathbf {x} }}...
network On a matrix form the previous is often approximated as a Mahalanobisdistance for a linear space as δ ( x ( i ) , x ( j ) ) ≈ ( x ( i ) − x (...
matrix, is S {\displaystyle \mathbf {S} } ), this generalizes to the Mahalanobisdistance between the two distributions: d ′ = ( μ a − μ b ) ′ Σ − 1 ( μ a...
ASTM E178: Standard Practice for Dealing With Outlying Observations Mahalanobisdistance and leverage are often used to detect outliers, especially in the...
Deviation (statistics) Distance correlation Distance standard deviation Error bar Geometric standard deviation Mahalanobisdistance generalizing number of...
{\displaystyle \mathbf {x} ^{\mathsf {T}}Q\mathbf {x} } (compare with the Mahalanobisdistance). In the Bayesian interpretation P {\displaystyle P} is the inverse...
comparison of performance of the Gaussian mixture distance with the well-known Euclidean and Mahalanobisdistances based on a precision performance measurement...
X\subset \mathbb {R} ^{n}} are squared generalized Euclidean distances (Mahalanobisdistance), that is, D f ( y , x ) = ( y − x ) T A ( y − x ) {\displaystyle...
Hotelling's T2 or Mahalanobisdistance). With such modified SIMCA methods, classification of an object requires both that its orthogonal distance from the model...
neuron. The norm is typically taken to be the Euclidean distance (although the Mahalanobisdistance appears to perform better with pattern recognition[editorializing])...
Multivariate statistics and Computer Science. Mahalanobis introduced the measure Mahalanobisdistance which is used in multivariate statistics and other...
covariance matrix of the data is sometimes used to define a distance metric called Mahalanobisdistance. Similarity learning is used in information retrieval...
called a "profile model", which looks for strong edges or uses the Mahalanobisdistance to match a model template for the point. Conform the suggested shape...
{n_{1}+n_{2}}{n_{1}n_{2}}}+{\frac {(g^{*})^{2}}{2(n_{1}+n_{2})}}.} Mahalanobisdistance (D) is a multivariate generalization of Cohen's d, which takes into...
defined for metrics other than Euclidean, such as the Mahalanobisdistance or Manhattan distance. However, in these cases the boundaries of the Voronoi...
continuous probability distributions; Chi distance a precursor and special case of the Mahalanobisdistance and P-value, defined as the probability measure...