Upgrading from:

MultivariateStatistics`

MultiPoissonDistribution has been renamed to MultivariatePoissonDistribution and is part of the built-in Mathematica kernel.
HotellingTSquareDistribution has been added to the built-in Mathematica kernel.
MultinormalDistribution has been added to the built-in Mathematica kernel.
MultivariateTDistribution has been added to the built-in Mathematica kernel.
MultinomialDistribution and NegativeMultinomialDistribution are now in the built-in kernel.
PrincipalComponents has been added to the built-in Mathematica kernel.

New system functions

MultiPoissonDistribution is now in the Mathematica kernel as MultivariatePoissonDistribution:

Version 7.0 << MultivariateStatistics` Mean[MultiPoissonDistribution[Subscript[\[Mu], 0], {Subscript[\[Mu], 1], Subscript[\[Mu], 2]}]]

HotellingTSquareDistribution is now available in the built-in Mathematica kernel:

Version 7.0 << MultivariateStatistics` Mean[HotellingTSquareDistribution[p, m]]

MultinormalDistribution is now available in the built-in Mathematica kernel:

Version 7.0 << MultivariateStatistics` Mean[MultinormalDistribution[{Subscript[\[Mu], 1], Subscript[\[Mu], 2]}, {{Subscript[\[Sigma], 11]^2, \[Rho]*Subscript[\[Sigma], 11]*Subscript[\[Sigma], 22]}, {\[Rho]*Subscript[\[Sigma], 11]*Subscript[\[Sigma], 22], Subscript[\[Sigma], 22]^2}}]]

MultivariateTDistribution is now available in the built-in Mathematica kernel:

Version 7.0 << MultivariateStatistics` Mean[MultivariateTDistribution[{{1, \[Rho]}, {\[Rho], 1}}, 10]]

MultinomialDistribution and NegativeMultinomialDistribution are now available in the built-in Mathematica kernel:

Version 7.0 << MultivariateStatistics` Mean[MultinomialDistribution[ n, {Subscript[p, 1], Subscript[p, 2], Subscript[p, 3]}]]
Version 7.0 << MultivariateStatistics` Mean[NegativeMultinomialDistribution[ n, {Subscript[p, 1], Subscript[p, 2], Subscript[p, 3]}]]

PrincipalComponents is now available in the built-in Mathematica kernel:

Version 7.0 << MultivariateStatistics` PrincipalComponents[{{1, 2}, {2, 3}, {4, 10}}]

To find the principal components of scaled columns, specify Method->Correlation as an option to PrincipalComponents:

Version 7.0 << MultivariateStatistics` PrincipalComponents[{{1, 2}, {2, 3}, {4, 10}}, Method -> Correlation]

Note that since singular vectors are not unique, numerical signs may differ from the results given in Mathematica 7.

KendallRankCorrelation is now in the Mathematica kernel as KendallTau:

Version 8.0 << MultivariateStatistics` KendallRankCorrelation[{1, 2, 3}, {3, 1, 6}]

SpearmanRankCorrelation is now in the Mathematica kernel as SpearmanRho:

Version 8.0 << MultivariateStatistics` SpearmanRankCorrelation[{1, 2, 3}, {3, 1, 6}]