In probability theory and directional statistics, a wrapped Lévy distribution is a wrapped probability distribution that results from the "wrapping" of the Lévy distribution around the unit circle.
The pdf of the wrapped Lévy distribution is
fWL
infty | ||
(\theta;\mu,c)=\sum | \sqrt{ | |
n=-infty |
c | |
2\pi |
where the value of the summand is taken to be zero when
\theta+2\pin-\mu\le0
c
\mu
fWL(\theta;\mu,c)=
1 | |
2\pi |
infty | |
\sum | |
n=-infty |
e-in(\theta-\mu)-\sqrt{c|n|(1-isgn{n})}=
1 | |
2\pi |
\left(1+
infty | |
2\sum | |
n=1 |
e-\sqrt{cn
In terms of the circular variable
z=ei\theta
\langle
n\rangle=\int | |
z | |
\Gamma |
ein\thetafWL(\theta;\mu,c)d\theta=ei(1-isgn(n))}.
where
\Gamma
2\pi
\langlez\rangle=ei\mu-\sqrt{c(1-i)}
The mean angle is
\theta\mu=Arg\langlez\rangle=\mu+\sqrt{c}
and the length of the mean resultant is
R=|\langlez\rangle|=e-\sqrt{c