Other Multivariate Normal Properties

Normal Distribution Properties

Property 1: If X and A are k × 1 column vectors and X N(μ, Σ), then

Property 1

Definition 1: The standard multivariate normal distribution is a multivariate normal distribution where the mean vector μ is the zero vector and the covariance matrix is the identity matrix.

To standardize a vector X, to obtain the standardized vector Z

Z = (UT)-1(Xμ)

you have two choices for U: (1) use the Cholesky decomposition Σ = UTU or (2) use the square root matrix U = Σ1/2 as described in Positive Definite Matrices. These choices exist since Σ is a positive definite matrix.

Property 2: X N(μ, Σ), then the standard vector Z N(0, I).

Property 3:

Property 3

Property 4: Suppose X and Y are independent k × 1 column vectors. If X N(μX, ΣX) and Y N(μY, ΣY), then

Central limit theorem formula

Property 5: If X1, …, XnN(μ, Σ) is a random sample then

Central limit theorem formula

Property 6 (Multivariate Central Limit Theorem): If X1, …, Xn  is a random sample from a population with mean μ and covariance matrix Σ, then for n sufficiently large 

Central limit theorem formula

This means that as n → ∞, the distribution of

Central limit theorem

See also Multivariate Central Limit Theorem.

Wishart Distribution

If X1, …, XnN(0, Σ)  are independent, then X12 + … + Xn2 is said to have a Wishart distribution with n degrees of freedom, denoted W(n, Σ).

Note that this is the multivariate counterpart to the chi-square distribution since if x1, …, xnN(0, 1) are independent, then x12 + … + xn2 ∼ χ2(n). We also know that (n–1)s22 ∼ χ2(n–1). The multivariate counterpart is

Property 7: If X1, …, XnN(0, Σ) is a random sample, then

Sample covariance and Wishart

where

Sample covariance matrix

References

Rencher, A.C. (2002) Methods of multivariate analysis (2nd Ed). Wiley-Interscience, New York.

Azevedo, C. L. N. (2016) The Multivariate Normal Distribution
https://www.ime.unicamp.br/~cnaber/mvnprop.pdf

Leave a Comment