Directional Statistics - Circular and Higher Dimensional Distributions

Circular and Higher Dimensional Distributions

Any probability density function on the line can be "wrapped" around the circumference of a circle of unit radius. That is, the pdf of the wrapped variable


\theta = x_w=x \mod 2\pi\ \ \in (-\pi,\pi]

is


p_w(\theta)=\sum_{k=-\infty}^{\infty}{p(\theta+2\pi k)}.

This concept can be extended to the multivariate context by an extension of the simple sum to a number of sums that cover all dimensions in the feature space:


p_w(\vec\theta)=\sum_{k_1=-\infty}^{\infty}\cdots \sum_{k_F=-\infty}^\infty{p(\vec\theta+2\pi k_1\mathbf{e}_1+\dots+2\pi k_F\mathbf{e}_F)}

where is the th Euclidean basis vector.

Read more about this topic:  Directional Statistics

Famous quotes containing the words circular, higher and/or dimensional:

    ‘A thing is called by a certain name because it instantiates a certain universal’ is obviously circular when particularized, but it looks imposing when left in this general form. And it looks imposing in this general form largely because of the inveterate philosophical habit of treating the shadows cast by words and sentences as if they were separately identifiable. Universals, like facts and propositions, are such shadows.
    David Pears (b. 1921)

    They say the seeds of what we will do are in all of us, but it always seemed to me that in those who make jokes in life the seeds are covered with better soil and with a higher grade of manure.
    Ernest Hemingway (1899–1961)

    I don’t see black people as victims even though we are exploited. Victims are flat, one- dimensional characters, someone rolled over by a steamroller so you have a cardboard person. We are far more resilient and more rounded than that. I will go on showing there’s more to us than our being victimized. Victims are dead.
    Kristin Hunter (b. 1931)