In probability theory and directional statistics, a wrapped exponential distribution is a wrapped probability distribution that results from the "wrapping" of the exponential distribution around the unit circle.
The probability density function of the wrapped exponential distribution is[1]
fWE
infty | |
(\theta;λ)=\sum | |
k=0 |
λe-λ=
λe-λ | |
1-e-2\pi |
,
for
0\le\theta<2\pi
λ>0
0\leX<2\pi
The characteristic function of the wrapped exponential is just the characteristic function of the exponential function evaluated at integer arguments:
\varphi | ||||
|
which yields an alternate expression for the wrapped exponential PDF in terms of the circular variable z=e i (θ-m) valid for all real θ and m:
\begin{align} fWE(z;λ) &=
1 | |
2\pi |
infty | |
\sum | |
n=-infty |
z-n | |
1-in/λ |
\\[10pt] &=\begin{cases}
λ | |
\pi |
|
&ifz ≠ 1 \\[12pt]
λ | |
1-e-2\piλ |
&ifz=1 \end{cases} \end{align}
where
\Phi
In terms of the circular variable
z=ei\theta
\langle
n\rangle=\int | |
z | |
\Gamma |
ein\thetafWE(\theta;λ)d\theta=
1 | |
1-in/λ |
,
where
\Gamma
2\pi
\langlez\rangle=
1 | |
1-i/λ |
.
The mean angle is
\langle\theta\rangle=Arg\langlez\rangle=\arctan(1/λ),
and the length of the mean resultant is
R=|\langlez\rangle|=
λ | |
\sqrt{1+λ2 |
and the variance is then 1-R.
The wrapped exponential distribution is the maximum entropy probability distribution for distributions restricted to the range
0\le\theta<2\pi
\operatorname{E}(\theta)