In probability theory and statistics, the normal-inverse-gamma distribution (or Gaussian-inverse-gamma distribution) is a four-parameter family of multivariate continuous probability distributions. It is the conjugate prior of a normal distribution with unknown mean and variance.
Suppose
x\mid\sigma2,\mu,λ\simN(\mu,\sigma2/λ)
\mu
\sigma2/λ
\sigma2\mid\alpha,\beta\sim\Gamma-1(\alpha,\beta)
(x,\sigma2)
(x,\sigma2)\simN-\Gamma-1(\mu,λ,\alpha,\beta).
(
NIG
N-\Gamma-1.
The normal-inverse-Wishart distribution is a generalization of the normal-inverse-gamma distribution that is defined over multivariate random variables.
f(x,\sigma2\mid\mu,λ,\alpha,\beta)=
\sqrt{λ | |
For the multivariate form where
x
k x 1
f(x,\sigma2\mid\mu,V-1,\alpha,\beta)=|V|-1/2{(2\pi)-k/2}
\beta\alpha | |
\Gamma(\alpha) |
\left(
1 | |
\sigma2 |
\right)\alpha\exp\left(-
2\beta+(x-\boldsymbol{\mu | |
) |
TV-1(x-\boldsymbol{\mu})}{2\sigma2}\right).
where
|V|
k x k
V
k=1
x,V,\boldsymbol{\mu}
It is also possible to let
\gamma=1/λ
f(x,\sigma2\mid\mu,\gamma,\alpha,\beta)=
1 | |
\sigma\sqrt{2\pi\gamma |
}
\beta\alpha | |
\Gamma(\alpha) |
\left(
1 | |
\sigma2 |
\right)\alpha\exp\left(-
2\gamma\beta+(x-\mu)2 | |
2\gamma\sigma2 |
\right)
In the multivariate form, the corresponding change would be to regard the covariance matrix
V
V-1
F(x,\sigma2\mid\mu,λ,\alpha,\beta)=
| |||||||||||||
|
)}{\sqrt{2}\sigma}\right)+1\right)}{2 \sigma2\Gamma(\alpha)}
Given
(x,\sigma2)\simN-\Gamma-1(\mu,λ,\alpha,\beta).
\sigma2
\sigma2\sim\Gamma-1(\alpha,\beta)
while
\sqrt{ | \alphaλ |
\beta |
2\alpha
In the multivariate case, the marginal distribution of
x
x\simt2\alpha(\boldsymbol{\mu},
\beta | |
\alpha |
V)
Suppose
(x,\sigma2)\simN-\Gamma-1(\mu,λ,\alpha,\beta).
Then for
c>0
(cx,c\sigma2)\simN-\Gamma-1(c\mu,λ/c,\alpha,c\beta).
Proof: To prove this let
(x,\sigma2)\simN-\Gamma-1(\mu,λ,\alpha,\beta)
c>0
Y=(Y1,Y2)=(cx,c\sigma2)
Y
(y1,y2)
1/c2
N-\Gamma-1(\mu,λ,\alpha,\beta)
(y1/c,y2/c)
Y
(y1,y2)
fY(y1,y
|
\sqrt{λ | |
The right hand expression is the PDF for a
N-\Gamma-1(c\mu,λ/c,\alpha,c\beta)
(y1,y2)
Normal-inverse-gamma distributions form an exponential family with natural parameters
style\theta | ||||
|
style\theta2=λ\mu
style\theta3=\alpha
style\theta | ||||
|
styleT | ||||
|
styleT | ||||
|
styleT3=log(
1 | |
\sigma2 |
)
styleT | ||||
|
Measures difference between two distributions.
See the articles on normal-gamma distribution and conjugate prior.
See the articles on normal-gamma distribution and conjugate prior.
Generation of random variates is straightforward:
\sigma2
\alpha
\beta
x
\mu
\sigma2/λ
\sigma2V
\sigma2