Scribd
Upload
150 views3 pages

Multivariate Laplace Distribution

The multivariate Laplace distribution is a generalization of the Laplace distribution to multiple variables. There are symmetric and asymmetric forms. The symmetric form has a characteristic function that depends on the mean vector and covariance matrix. Marginal distributions are Laplace distributed. The asymmetric form also depends on the mean and covariance matrix, with marginals being asymmetric Laplace distributed and non-zero skewness. Both can model data with heavier tails than the normal distribution.

Uploaded by

anthony777
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
150 views3 pages

Multivariate Laplace Distribution

The multivariate Laplace distribution is a generalization of the Laplace distribution to multiple variables. There are symmetric and asymmetric forms. The symmetric form has a characteristic function that depends on the mean vector and covariance matrix. Marginal distributions are Laplace distributed. The asymmetric form also depends on the mean and covariance matrix, with marginals being asymmetric Laplace distributed and non-zero skewness. Both can model data with heavier tails than the normal distribution.

Uploaded by

anthony777
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 3

Multivariate Laplace distribution

In the mathematical theory of probability, multivariate Laplace distributions are extensions of the
Laplace distribution and the asymmetric Laplace distribution to multiple variables. The marginal
distributions of symmetric multivariate Laplace distribution variables are Laplace distributions. The
marginal distributions of asymmetric multivariate Laplace distribution variables are asymmetric Laplace
distributions.[1]

Symmetric multivariate Laplace distribution


A typical characterization of the Multivariate Laplace (symmetric)
symmetric multivariate Laplace
Parameters μ ∈ Rk — location
distribution has the characteristic
Σ ∈ Rk×k — covariance (positive-definite matrix)
function:
Support x ∈ μ + span(Σ) ⊆ Rk
PDF
If ,

where is the vector of means for


each variable and is the where and is the modified
covariance matrix.[2] Bessel function of the second kind.

Unlike the multivariate normal


Mean μ
distribution, even if the covariance
matrix has zero covariance and Mode μ
correlation the variables are not Variance Σ
independent.[1] The symmetric
Skewness 0
multivariate Laplace distribution is
elliptical.[1] CF

Probability density
function

If , the probability density function (pdf) for a k-dimensional multivariate Laplace distribution
becomes:

where:

and is the modified Bessel function of the second kind.[1]

In the correlated bivariate case, i.e., k = 2, with the pdf reduces to:
where:

and are the standard deviations of and , respectively, and is the correlation coefficient of
and . [1]

For the uncorrelated bivariate Laplace case, that is k  =  2, and , the pdf
becomes:

[1]

Asymmetric multivariate Laplace distribution


A typical characterization Multivariate Laplace (asymmetric)
of the asymmetric
Parameters μ ∈ Rk — location
multivariate Laplace
Σ ∈ Rk×k — covariance (positive-definite matrix)
distribution has the
characteristic function: Support x ∈ μ + span(Σ) ⊆ Rk
PDF

where and is the modified Bessel function of


the second kind.
Mean μ
Variance Σ+μ'μ
Skewness non-zero unless μ=0
CF

[1]

As with the symmetric multivariate Laplace distribution, the asymmetric multivariate Laplace distribution
has mean , but the covariance becomes .[3] The asymmetric multivariate Laplace distribution is
not elliptical unless , in which case the distribution reduces to the symmetric multivariate Laplace
distribution with .[1]

The probability density function (pdf) for a k-dimensional asymmetric multivariate Laplace distribution is:

where:
and is the modified Bessel function of the second kind.[1]

The asymmetric Laplace distribution, including the special case of , is an example of a geometric
[3]
stable distribution. It represents the limiting distribution for a sum of independent, identically distributed
random variables with finite variance and covariance where the number of elements to be summed is itself
an independent random variable distributed according to a geometric distribution.[1] Such geometric sums
can arise in practical applications within biology, economics and insurance.[1] The distribution may also be
applicable in broader situations to model multivariate data with heavier tails than a normal distribution but
finite moments.[1]

The relationship between the exponential distribution and the Laplace distribution allows for a simple
method for simulating bivariate asymmetric Laplace variables (including for the case of ). Simulate a
bivariate normal random variable vector from a distribution with and covariance matrix
. Independently simulate an exponential random variables W from an Exp(1) distribution.
will be distributed (asymmetric) bivariate Laplace with mean and covariance
matrix . [1]

References
1. Kotz. Samuel; Kozubowski, Tomasz J.; Podgorski, Krzysztof (2001). The Laplace
Distribution and Generalizations. Birkhauser. pp. 229–245. ISBN 0817641661.
2. Fragiadakis, Konstantinos & Meintanis, Simos G. (March 2011). "Goodness-of-fit tests for
multivariate Laplace distributions" (https://doi.org/10.1016%2Fj.mcm.2010.10.014).
Mathematical and Computer Modelling. 53 (5–6): 769–779. doi:10.1016/j.mcm.2010.10.014
(https://doi.org/10.1016%2Fj.mcm.2010.10.014).
3. Kozubowski, Tomasz J.; Podgorski, Krzysztof; Rychlik, Igor (2010). "Multivariate Generalize
Laplace Distributions and Related Random Fields" (https://pdfs.semanticscholar.org/7c5b/7f
c2d0756ad5a161922a9b439e12ccfb51eb.pdf) (PDF). Journal of Multivariate Analysis.
University of Gothenburg. 113: 59–72. doi:10.1016/j.jmva.2012.02.010 (https://doi.org/10.10
16%2Fj.jmva.2012.02.010). S2CID 206252976 (https://api.semanticscholar.org/CorpusID:20
6252976). Retrieved 2017-05-28.

Retrieved from "https://en.wikipedia.org/w/index.php?title=Multivariate_Laplace_distribution&oldid=1142746935"

You might also like

pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy