Rayleigh distributions of a random variable

The distribution is named after Lord Rayleigh

Definition:- The Rayleigh distribution is a continuous probability distribution for non-negative-

valued random variables it is the distribution of the magnitude of the two dimenssional random
vector whose co-ordinates are independent,identically distributed ,and zero mean normally
distributed with equal variance . A Rayleigh distribution is often observed when the overall magnitude of a
vector is related to its directional components.

The probability density function of the Rayleigh distribution(pdf)

Definition:- The probability density function of the Rayleigh distribution(pdf) is

x −1/ 2( σ )
2
x

f ( x , σ )= 2 e
σ
whereσ is the scale parameter of the distribution.
The cumulative distribution function Rayleigh distribution(cdf)
Definition:-  The cumulative density function of the Rayleigh distribution(cdf) is
( σx )
2
−1/ 2
F ( x , σ )=1−e
For x=( 0 , ∞ )
Proof
Consider the two dimensional vector Y=(U,V) which has components that are bivarriate
normally distributed,centered zero,and independent then Uand V have density functions
( σx ) since it is Gaussian(normal) distribution
2

fu ( x , σ )=fv ( x , σ ) =1/ √2 π σ 2 e
−1 /2

with zero mean and identically distributed

Let X be the length of Y . That is, X=√ u2 +v 2 .Then has cumulative distribution function
∞
Fx ( x , σ )=∬ fu ( x , σ ) fv ( x , σ ) dA
Dx

In short Dx=(u,v;√ u +v ≤ x ) and dA=dudv

2 2

Since U and V independent i.e f(x1,x2)=f(x1)f(x2)

∞
Fx ( x , σ )=∬ f ( u ) f ( v ) dA
Dx

(σu ) 2 ( vσ )
2 2
∞
−1 /2 −1/ 2
Fx ( x , σ )=∬ 1 / √ 2 π σ e 2
dA∗1/ √ 2 π σ e 2
dA
Dx
∞

∬ 1/2 π ( σ 2)e−(u +v)/2 πσ 2

Dx

Let u=rcosθ∧v=rsinθ since our distribution is in polar coordinate tan−1 ¿

From jacobian change of variable techinique transformation of two variables
u,v with partial differentiation interms of θ∧r
 Jacobiaans transformation(J)= av /ar av /aθ = −rsinθ rcosθ |au/ar au/aθ
| | cosθ |
−rsinθ

This is 2*2 determinant its J=r ¿

Then its J=r since ( sin θ )2 + ( cosθ )2=1
For that value f ( r , θ ) =r (u , v )
Writing the double integral in polar coordinates, it becomes
( σr )
2
−
FX ( x , σ )=1 /2 πσ
2
∬re drdθ

()
2
r −r
Let u=−1/2 σ du/dr= σ 2 ∧−σ 2 du=rdr u=0 to – x 2 /2 σ 2∧θ=0 ¿ 2 π
2 2
θ =2 π r=−x / 2 σ
1
FX ( x , σ )= ∬ 2
e (−σ ) dudθ
u 2

θ=0 r =0 2π σ
By using integration by part we get
2
−x
FX ( x , σ )=cdf =1−e σ and from above we get its pdf by derivating d/dx( FX ( x , σ )
2
−x
=d/dx(1−e σ
¿
x −( )
2
x

Finally we get fx(x,σ )= 2 e 2 σ

(σ )
Expectation/mean/ Rayleigh distribution

Definition:-  the expectation or mean of Rayleigh distribution E(X) is

E ( X ) =σ √ π /2
Proof
∞
We know that fX ( x )=∫ x x /σ e
2 −¿¿
for x≥0 , σ ≥ 0
−∞
∞ ∞
Then E ( X ) =∫ x fX ( x ) onthis E ( X ) =∫ x x /σ e
2 −¿ ¿
from the definition
−∞ −∞
∞ ∞
E ( X ) =∫ x fX ( x )=∫ x x /σ e
2 −¿¿
¿
0 0
∞
=1/σ
2
∫ x x e−¿¿ ¿ we do integration by part
0
∞
=1/σ x ∫ x e
2 −¿¿
¿
0
∞
Let ∫ x e
2 2
−b( x ) −b( x )
=1/2 b e based onthis integral formula
0
 { ( σx ) } ∫ − ∫ 1/2(−2 σ ¿¿)e ( xσ )
2 2
∞ ∞
−1/ 2 −1/ 2
1/ σ x (−2 σ ) e ¿ ¿dx
2 2 2

x=0 x=0
2
∞ ∞ −x
1
=0+∫ e dx =( √ 2 π σ )∫ e
2 2
−x / 2 σ 2 2σ
2¿

¿ dx
0 √2 π σ 2 0

E(X)=√ 2 π σ 2 /2= σ ¿
So the E(X)=√ 2 π σ 2 /2= σ ¿ Expectation/mean/of Rayleigh distribution
Variance of Rayleigh distribution
Definition:-  the expectation or mean of Rayleigh distribution Var[X] is
∞ ∞

Var [ X ] =E [ x ] −[ E ( x ) ] = ∫ x fX ( x ) dx =∫ x fX ( x ) dx
2 2 2 2

−∞ 0

−1/ 2( )
2
∞ x
2 x
∫ (σ 2 )
x e
σ
dx by using integration by part
0

−1/2 ( )
x −1 /2 ( σ )
2 2
∞ x ∞ x

x 2∫ 2 e -2 x ∫ x2 e σ dx
0 (σ ) 0 (σ )
∞

Remember that ∫ x e−b( x )=1/2 b e−b( x ) our integration simplified to

2 2

( xσ ) −1 /2( )
2 2
∞ x
1
( ) ()
−1 /2
1 1
x2 2
(−2σ 2 ) e {for x=0−∞ }−∫ 2 x 2 (−2 σ 2)e σ
dx
2σ 0 σ 2
( σx )
2
∞
−1/ 2
=0+∫ x e dx rember from above
0

=2(-2σ )( 12 )e ( σ ) {for x=0--∞ }=0+2σ 2 e−1 /2( σ ) {for x=0--∞ }

2
x 2
−1/ 2 x
2

( σx )
2
∞
1 π
=√ 2 π σ
−1 /2
=(2− 2 )σ
2
∫e
2 2
22 σ
√2 π σ 0

=(2− 2 ) σ
∞ ∞
π
So Var [ X ] =E [ x ] −[ E ( x ) ] = ∫ x fX ( x ) dx =∫ x fX ( x ) dx
2 2 2 2 2

−∞ 0

PROPERTIES of Rayleigh distribution

1. Rayleigh distribution is a continuous probability distribution for nonnegative-valued

random variables.because it pdf,and cdf value obtained (0¿ ∞)
2. The mean of a Rayleigh random variable is thus:-
μ=σ ¿

3. The variance of a Rayleigh random variable is:-Var [ X ] =E [ x ]−[ E ( x ) ] =(2− 2 ) σ

2 2 π 2

4. The standard deviation of a Rayleigh random variable is:√ Var (x)=√ 2−π /2 σ

5. Mode ( ơ)is the maximum pdf of Rayleigh random variable

1 0.606
f ( σ , σ )= =
−1
2
σ
σe

6. If X has an exponential distribution X e , then Y=√ X ¿ )

α

7. Given a random variate U drawn from the uniform distribution in the interval (0, 1), then
the variate =σ √ −2 ln U

8. The chi distribution with v = 2 is equivalent to the Rayleigh Distribution with σ = 1.

9. The half-normal distribution is the univariate special case of the Rayleigh distribution

Application Area of Rayleigh distribution

 When analyzing wind velocity in two dimension
 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 weapon's precision.
In physical oceanography, the distribution of significant wave height
approximately follows a Rayleigh distribution