Rayleigh distribution

Relation to random vector length

Consider the two-dimensional vector ${\displaystyle Y=(U,V)}$ which has components that are bivariate normally distributed, centered at zero, with equal variances ${\displaystyle {\sigma }^2}$, and independent. Then ${\displaystyle U}$ and ${\displaystyle V}$ have density functions

${\displaystyle f_U(x;\sigma )=f_V(x;\sigma )=\frac{e^{-x^2/(2{\sigma }^2)}}{\sqrt{2\pi {\sigma }^2}}.}$

Let ${\displaystyle X}$ be the length of ${\displaystyle Y}$. That is, ${\displaystyle X=\sqrt{U^2+V^2}.}$ Then ${\displaystyle X}$ has cumulative distribution function

${\displaystyle F_X(x;\sigma )={\iint }_{D_x}{f}_U(u;\sigma )f_V(v;\sigma )dA,}$

where ${\displaystyle D_x}$ is the disk

${\displaystyle D_x=\left\{(u,v):\sqrt{u^2+v^2}\le x\right\}.}$

Writing the double integral in polar coordinates, it becomes

${\displaystyle F_X(x;\sigma )=\frac{1}{2\pi {\sigma }^2}{\int }_0^{2\pi }{\int }_0^{x}r{e}^{-r^2/(2{\sigma }^2)}drd\theta =\frac{1}{{\sigma }^2}{\int }_0^{x}r{e}^{-r^2/(2{\sigma }^2)}dr.}$

Finally, the probability density function for ${\displaystyle X}$ is the derivative of its cumulative distribution function, which by the fundamental theorem of calculus is

${\displaystyle f_X(x;\sigma )=\frac{d}{dx}{F}_X(x;\sigma )=\frac{x}{{\sigma }^2}{e}^{-x^2/(2{\sigma }^2)},}$

which is the Rayleigh distribution. It is straightforward to generalize to vectors of dimension other than 2. There are also generalizations when the components have unequal variance or correlations (Hoyt distribution), or when the vector Y follows a bivariate Student t-distribution (see also: Hotelling's T-squared distribution).

Properties

The raw moments are given by:

${\displaystyle {\mu }_j={\sigma }^j{2}^{j/2}\mathrm{\Gamma }\left(1+\frac{j}{2}\right),}$

where ${\displaystyle \mathrm{\Gamma }(z)}$ is the gamma function.

The mean of a Rayleigh random variable is thus :

${\displaystyle \mu (X)=\sigma \sqrt{\frac{\pi }{2}}\approx 1.253\sigma .}$

The standard deviation of a Rayleigh random variable is:

${\displaystyle \mathrm{std}(X)=\sqrt{\left(2-\frac{\pi }{2}\right)}\sigma \approx 0.655\sigma }$

The variance of a Rayleigh random variable is :

${\displaystyle \mathrm{var}(X)={\mu }_2-{\mu }_1^2=\left(2-\frac{\pi }{2}\right){\sigma }^2\approx 0.429{\sigma }^2}$

The mode is ${\displaystyle \sigma ,}$ and the maximum pdf is

${\displaystyle f_{max}=f(\sigma ;\sigma )=\frac{1}{\sigma }{e}^{-1/2}\approx \frac{0.606}{\sigma }.}$

The skewness is given by:

${\displaystyle {\gamma }_1=\frac{2\sqrt{\pi }(\pi -3)}{(4-\pi {)}^{3/2}}\approx 0.631}$

The excess kurtosis is given by:

${\displaystyle {\gamma }_2=-\frac{6{\pi }^2-24\pi +16}{(4-\pi {)}^2}\approx 0.245}$

The characteristic function is given by:

${\displaystyle \phi (t)=1-\sigma t{e}^{-\frac{1}{2}{\sigma }^2{t}^2}\sqrt{\frac{\pi }{2}}\left[\mathrm{erfi}\left(\frac{\sigma t}{\sqrt{2}}\right)-i\right]}$

where ${\displaystyle \mathrm{erfi}(z)}$ is the imaginary error function. The moment generating function is given by

${\displaystyle M(t)=1+\sigma t{e}^{\frac{1}{2}{\sigma }^2{t}^2}\sqrt{\frac{\pi }{2}}\left[\mathrm{erf}\left(\frac{\sigma t}{\sqrt{2}}\right)+1\right]}$

where ${\displaystyle \mathrm{erf}(z)}$ is the error function.

Differential entropy

The differential entropy is given by

${\displaystyle H=1+\ln \left(\frac{\sigma }{\sqrt{2}}\right)+\frac{\gamma }{2}}$

where ${\displaystyle \gamma }$ is the Euler–Mascheroni constant.

Parameter estimation

Given a sample of N independent and identically distributed Rayleigh random variables ${\displaystyle x_i}$ with parameter ${\displaystyle \sigma }$,

${\displaystyle \widehat{{\sigma }^2}=\frac{1}{2N}\sum _{i=1}^N{x}_i^2}$ is the maximum likelihood estimate and also is unbiased.

${\displaystyle \hat{\sigma }\approx \sqrt{\frac{1}{2N}\sum _{i=1}^N{x}_i^2}}$ is a biased estimator that can be corrected via the formula

${\displaystyle \sigma =\hat{\sigma }\frac{\mathrm{\Gamma }(N)\sqrt{N}}{\mathrm{\Gamma }\left(N+\frac{1}{2}\right)}=\hat{\sigma }\frac{4^{N}N!(N-1)!\sqrt{N}}{(2N)!\sqrt{\pi }}}$ ${\displaystyle =\frac{\hat{\sigma }}{c_4(2N+1)}}$, where c₄ is the correction factor used to unbias estimates of standard deviation for normal random variables.

Confidence intervals

To find the (1 − α) confidence interval, first find the bounds ${\displaystyle [a,b]}$ where:

${\displaystyle P\left({\chi }_{2N}^2\le a\right)=\alpha /2,P\left({\chi }_{2N}^2\le b\right)=1-\alpha /2}$

then the scale parameter will fall within the bounds

${\displaystyle \frac{N\overline{x^2}}{b}\le \widehat{{\sigma }^2}\le \frac{N\overline{x^2}}{a}}$

Generating random variates

Given a random variate U drawn from the uniform distribution in the interval (0, 1), then the variate

${\displaystyle X=\sigma \sqrt{-2\ln U}}$

has a Rayleigh distribution with parameter ${\displaystyle \sigma }$. This is obtained by applying the inverse transform sampling-method.

Related distributions

• ${\displaystyle R\sim \mathrm{R}\mathrm{a}\mathrm{y}\mathrm{l}\mathrm{e}\mathrm{i}\mathrm{g}\mathrm{h}(\sigma )}$ is Rayleigh distributed if ${\displaystyle R=\sqrt{X^2+Y^2}}$, where ${\displaystyle X\sim N(0,{\sigma }^2)}$ and ${\displaystyle Y\sim N(0,{\sigma }^2)}$ are independent normal random variables. This gives motivation to the use of the symbol ${\displaystyle \sigma }$ in the above parametrization of the Rayleigh density.
• The magnitude ${\displaystyle |z|}$ of a standard complex normally distributed variable z is Rayleigh distributed.
• The chi distribution with v = 2 is equivalent to the Rayleigh Distribution with σ = 1: ${\displaystyle R(\sigma )\sim \sigma {\chi }_2^{}.}$
• If ${\displaystyle R\sim \mathrm{R}\mathrm{a}\mathrm{y}\mathrm{l}\mathrm{e}\mathrm{i}\mathrm{g}\mathrm{h}(1)}$, then ${\displaystyle R^2}$ has a chi-squared distribution with 2 degrees of freedom: ${\displaystyle [Q=R(\sigma {)}^2]\sim {\sigma }^2{\chi }_2^2.}$
• If ${\displaystyle R\sim \mathrm{R}\mathrm{a}\mathrm{y}\mathrm{l}\mathrm{e}\mathrm{i}\mathrm{g}\mathrm{h}(\sigma )}$, then ${\displaystyle \sum _{i=1}^N{R}_i^2}$ has a gamma distribution with integer scale parameter ${\displaystyle N}$ and rate parameter ${\displaystyle \frac{1}{2{\sigma }^2}}$

  ${\displaystyle \left[Y=\sum _{i=1}^N{R}_i^2\right]\sim \mathrm{\Gamma }\left(N,\frac{1}{2{\sigma }^2}\right)}$ with integer shape parameter N and rate parameter ${\displaystyle \frac{1}{2{\sigma }^2}.}$

  ${\displaystyle \left[Y=\sum _{i=1}^N{R}_i^2\right]\sim \mathrm{\Gamma }\left(N,2{\sigma }^2\right)}$ with integer shape parameter N and scale parameter ${\displaystyle 2{\sigma }^2.}$

• The Rice distribution is a noncentral generalization of the Rayleigh distribution: ${\displaystyle \mathrm{R}\mathrm{a}\mathrm{y}\mathrm{l}\mathrm{e}\mathrm{i}\mathrm{g}\mathrm{h}(\sigma )=\mathrm{R}\mathrm{i}\mathrm{c}\mathrm{e}(0,\sigma )}$.
• The Weibull distribution with the shape parameter k = 2 yields a Rayleigh distribution. Then the Rayleigh distribution parameter ${\displaystyle \sigma }$ is related to the Weibull scale parameter according to ${\displaystyle \lambda =\sigma \sqrt{2}.}$
• If ${\displaystyle X}$ has an exponential distribution ${\displaystyle X\sim \mathrm{E}\mathrm{x}\mathrm{p}\mathrm{o}\mathrm{n}\mathrm{e}\mathrm{n}\mathrm{t}\mathrm{i}\mathrm{a}\mathrm{l}(\lambda )}$, then ${\displaystyle Y=\sqrt{X}\sim \mathrm{R}\mathrm{a}\mathrm{y}\mathrm{l}\mathrm{e}\mathrm{i}\mathrm{g}\mathrm{h}(1/\sqrt{2\lambda }).}$
• The half-normal distribution is the one-dimensional equivalent of the Rayleigh distribution.
• The Maxwell–Boltzmann distribution is the three-dimensional equivalent of the Rayleigh distribution.

Applications

An application of the estimation of σ can be found in magnetic resonance imaging (MRI). As MRI images are recorded as complex images but most often viewed as magnitude images, the background data is Rayleigh distributed. Hence, the above formula can be used to estimate the noise variance in an MRI image from background data.

The Rayleigh distribution was also employed in the field of nutrition for linking dietary nutrient levels and human and animal responses. In this way, the parameter σ may be used to calculate nutrient response relationship.

In the field of ballistics, the Rayleigh distribution is used for calculating the circular error probable—a measure of a gun's precision.

In physical oceanography, the distribution of significant wave height approximately follows a Rayleigh distribution.