Noncentral chi distribution

Noncentral chi
Parameters

k>0 degrees of freedom

λ>0
Support x∈[0;+∞)
PDF e−(x2+λ2)/2xkλ(λx)k/2Ik/2−1(λx)
CDF 1−Qk2(λ,x) with Marcum Q-function QM(a,b)
Mean π2L1/2(k/2−1)(−λ22)
Variance k+λ2−μ2, where μ is the mean

In probability theory and statistics, the noncentral chi distribution is a noncentral generalization of the chi distribution. It is also known as the generalized Rayleigh distribution.

Definition

If Xi are k independent, normally distributed random variables with means μi and variances σi2, then the statistic

Z=∑i=1k(Xiσi)2

is distributed according to the noncentral chi distribution. The noncentral chi distribution has two parameters: k which specifies the number of degrees of freedom (i.e. the number of Xi), and λ which is related to the mean of the random variables Xi by:

λ=∑i=1k(μiσi)2

Properties

Probability density function

The probability density function (pdf) is

f(x;k,λ)=e−(x2+λ2)/2xkλ(λx)k/2Ik/2−1(λx)

where Iν(z) is a modified Bessel function of the first kind.

Raw moments

The first few raw moments are:

μ1'=π2L1/2(k/2−1)(−λ22)
μ2'=k+λ2
μ3′=3π2L3/2(k/2−1)(−λ22)
μ4'=(k+λ2)2+2(k+2λ2)

where Ln(a)(z) is a Laguerre function. Note that the 2nth moment is the same as the nth moment of the noncentral chi-squared distribution with λ being replaced by λ2.

Bivariate non-central chi distribution

Let Xj=(X1j,X2j),j=1,2,…n, be a set of n independent and identically distributed bivariate normal random vectors with marginal distributions N(μi,σi2),i=1,2, correlation ρ, and mean vector and covariance matrix

E(Xj)=μ=(μ1,μ2)T,Σ=[σ11σ12σ21σ22]=[σ12ρσ1σ2ρσ1σ2σ22],

with Σ positive definite. Define

U=[∑j=1nX1j2σ12]1/2,V=[∑j=1nX2j2σ22]1/2.

Then the joint distribution of U, V is central or noncentral bivariate chi distribution with n degrees of freedom. If either or both μ1≠0 or μ2≠0 the distribution is a noncentral bivariate chi distribution.