# MultinormalDistribution

represents a multivariate normal (Gaussian) distribution with mean vector μ and covariance matrix Σ.

represents a multivariate normal distribution with zero mean and covariance matrix Σ.

# Details

• The probability density for vector in a multivariate normal distribution is proportional to .
• MultinormalDistribution allows μ to be any vector of real numbers, and Σ any symmetric positive definite × matrix of real numbers with p=Length[μ].
• The mean vector μ and covariance matrix Σ can be quantities such that μμ and Σ have the same unit dimensions componentwise. »
• MultinormalDistribution can be used with such functions as Mean, CDF, and RandomVariate.

# Background & Context

• represents a continuous multivariate statistical distribution supported over the set of of all -tuples and characterized by the property that each of the (univariate) marginal distributions is a NormalDistribution for . In other words, each of the variables satisfies for . The multinormal distribution is parametrized by a vector μ of real numbers and by a positive definite symmetric matrix Σ, which satisfy nLength[μ]Length[Σ] and which define the associated mean, variance, and covariance of the distribution. The multinormal distribution is sometimes referred to as the multivariate normal distribution, as a result of the fact that its univariate marginals are normally distributed.
• The probability density function (PDF) of a multinormal distribution has a single absolute maximum, though like the binormal distribution (BinormalDistribution) it may have multiple "peaks" (i.e. relative maxima). In general, the tails of each of the associated marginal PDFs are "thin" in the sense that the marginal PDF decreases exponentially rather than algebraically for large values of . (This behavior can be made quantitatively precise by analyzing the SurvivalFunction of these marginal distributions.)
• Most of the applications of the multinormal distribution correspond to the cases (BinormalDistribution) or rather than the general multinormal case. However, as a result of the multivariate central limit theorem, the multivariate normal distribution can be used to describe (at least qualitatively) any set of real-valued random variables, each of whose variates cluster around a given mean value. Even so, the bulk of the earliest literature (some of which dates back to the early 1800s) on multivariable extensions of the normal distribution focus on the bivariate and trivariate cases, which are applied in a wide range of fields, including genetics, materials science, evolutionary biology, economics, ecology, and medicine.
• RandomVariate can be used to give one or more machine- or arbitrary-precision (the latter via the WorkingPrecision option) pseudorandom variates from a multinormal distribution. Distributed[x,MultinormalDistribution[μ,Σ]] , written more concisely as xMultinormalDistribution[μ,Σ], can be used to assert that a random variable x is distributed according to a multinormal distribution. Such an assertion can then be used in functions such as Probability, NProbability, Expectation, and NExpectation.
• The probability density and cumulative distribution functions for multinormal distributions may be given using PDF[MultinormalDistribution[μ,Σ],x] and CDF[MultinormalDistribution[μ,Σ],x]. The mean, median, variance, raw moments, and central moments may be computed using Mean, Median, Variance, Moment, and CentralMoment, respectively.
• DistributionFitTest can be used to test if a given dataset is consistent with a multinormal distribution, EstimatedDistribution to estimate a multinormal parametric distribution from given data, and FindDistributionParameters to fit data to a multinormal distribution. ProbabilityPlot can be used to generate a plot of the CDF of given data against the CDF of a symbolic multinormal distribution and QuantilePlot to generate a plot of the quantiles of given data against the quantiles of a symbolic multinormal distribution.
• TransformedDistribution can be used to represent a transformed multinormal distribution, CensoredDistribution to represent the distribution of values censored between upper and lower values, and TruncatedDistribution to represent the distribution of values truncated between upper and lower values. CopulaDistribution can be used to build higher-dimensional distributions that contain a multinormal distribution, and ProductDistribution can be used to compute a joint distribution with independent component distributions involving multinormal distributions.
• MultinormalDistribution is related to a number of other distributions, including the NormalDistribution and BinormalDistribution, as discussed above. The one-dimensional marginals of a MultinormalDistribution have a NormalDistribution, while each of the multivariate marginals is again an instance of MultinormalDistribution. MultinormalDistribution is a limiting case of MultivariateTDistribution in the sense that PDF[MultinormalDistribution[{μ1,μ2},{{1,ρ},{ ρ,1}}],{x,y}] is precisely the limit of PDF[MultivariateTDistribution[{μ1,μ2},{{1,ρ},{ ρ,1}},ν],{x,y}] as ν. Moreover, MultinormalDistribution can be obtained from LogMultinormalDistribution by a transformation (TransformedDistribution). MultinormalDistribution is also related to RiceDistribution and, because of its relation to the univariate NormalDistribution, is also related to LogNormalDistribution, DavisDistribution, LogLogisticDistribution, ExponentialDistribution, WeibullDistribution, GompertzMakehamDistribution, ExtremeValueDistribution, and GammaDistribution.

# Examples

open allclose all

## Basic Examples(4)

Probability density function:

 In[2]:=
 Out[2]=
 In[3]:=
 Out[3]=

Cumulative distribution function:

 In[1]:=
 Out[1]=

Mean and variance:

 In[1]:=
 In[2]:=
 Out[2]=
 In[3]:=
 Out[3]=

Covariance:

 In[1]:=
 In[2]:=
 Out[2]=