Kernel density estimation of circular data with a von Mises kernel
Kernel density estimation of circular data with a von Mises kernel.
vm.kde(u, h, thumb = "none", rads = TRUE)
u |
A numeric vector containing the data. |
h |
The bandwidth. |
thumb |
It can be either "none", so the bandwidth the user has set will be used, "tay" for the method of Taylor (2008) or "rot" for the method of Garcia-Portugues (2013). |
rads |
If the data are in radians, this should be TRUE and FALSE otherwise. |
The user has the option to use a bandwidth he/she has found in some way (cross-validation) or estimate it as Taylor (2008) or Garcia-Portugues (2013).
A list including:
h |
The bandwidth. If the user chose one of "tay" or "rot" the estimated bandwidth will be returned. |
f |
The kernel density estimate at the observed points. |
Michail Tsagris
R implementation and documentation: Michail Tsagris mtsagris@uoc.gr and Giorgos Athineou<gioathineou@gmail.com>
Taylor, C. C. (2008). Automatic bandwidth selection for circular density estimation. Computational Statistics & Data Analysis, 52(7): 3493-3500.
Garcia Portugues, E. (2013). Exact risk improvement of bandwidth selectors for kernel density estimation with directional data. Electronic Journal of Statistics, 7, 1655-1685.
x <- rvonmises(100, 2.4, 10, rads = TRUE) hist(x, freq = FALSE) f1 <- vm.kde(x, h = 0.1, thumb = "rot", rads = TRUE)$f f2 <- vm.kde(x, h = 0.1, thumb = "tay", rads = TRUE)$f h <- vmkde.tune(x)[1] f3 <- vm.kde(x, h = h, thumb = "none", rads = TRUE)$f points(x, f1, col = 1) points(x, f2, col = 2) points(x, f3, col = 3)
Please choose more modern alternatives, such as Google Chrome or Mozilla Firefox.