Multidimensional Normal (Gaussian)
Distribution
Centralized (unnormalized) multidimensional Normal (Gaussian)
distribution is denoted by: N(0, K) where the mean is 0
(zero) and the
covariance matrix is K = ( Ki,j
) = Cov(Xi, Xj) . K is symmetric by the identity, i.e., Cov(Xi,
Xj) = Cov(Xj , Xi) . Let X = [X1,
X2, X3, ...Xn]T and n-dimensional derivatives are
written as
.
The density function of N(0, K)
is exp ( -1/2 XT K-1
X ),
normalizing constant of the N(0, K)
density is:
|
(1) |
where |K| = det( K
) is the determinant. In general, if multidimensional Gaussian is not
centered
then the (possibly offset) density has the form: exp [ -1/2 (X-μ)T K-1 (X-μ) ].
- Because K-1 is real and symmetric (since (K-1)T
= (KT)-1 ), if A = K
we can decompose
A into A
= T Λ T-1,
where T is an orthonormal matrix ( TT
T = I ) of the eigenvectors of A and Λ is a diagonal
matrix of
the eigenvalues of A.
Then the multidimensional Gaussian density can be expressed as:
|
(2) |
However, T
is
orthonormal and we have T-1 = TT
. Now define a new vector variable Y = TT
X, and substitute in (2):
where | J | is the determinant of the Jacobian
matrix J = ( Jm,n ) = ( ∂Xm
/ ∂Yn). As X = (TT)-1Y
= Y , J ≡ T and thus | J |
= 1.
- Because Λ
is diagonal, the integral (4) may be separated into the product of n
independent Gaussians, each of which we can integrate separately using
the 1D Gaussian:
|
(5) |
Summarizing:
Orthonormal matrix multiplication does not change the determinant,
so we
have
| A | = | T Λ T-1| = | T | | Λ | | T-1| =
| Λ |
And therefore:
|
(10) |
Substituting back in for K-1 ( A = K and | K-1 | = 1 / |K| ), we get
|
(11) |
as we expected.
Last modified
on
GMT by