mle.vonmisesmix {cylcop} | R Documentation |
Mixed von Mises Maximum Likelihood Estimates
Description
Computes the maximum likelihood estimates for the parameters of a mixed
von Mises distribution: the mean directions, the concentration parameters,
and the proportions of the distributions. The code is a simplified version of
movMF::movMF()
with the added
feature of optionally fixed mean directions (Hornik and Grün 2014).
Usage
mle.vonmisesmix(theta, mu = NULL, ncomp = 2)
Arguments
theta |
|
mu |
(optional) numeric vector of length |
ncomp |
positive integer specifying the number of components of the mixture model. |
Details
The function complements the 'circular' package, which
provides functions to make maximum likelihood estimates of e.g. von Mises
(circular::mle.vonmises()
), or wrapped Cauchy distributions
(circular::mle.wrappedcauchy()
)
Value
A list containing the optimized parameters mu
, kappa
,
and prop
.
References
Hornik K, Grün B (2014). “movMF : An R Package for Fitting Mixtures of von Mises-Fisher Distributions.” Journal of Statistical Software, 58. doi:10.18637/jss.v058.i10..
See Also
movMF::movMF()
,
circular::mle.vonmises()
,
dvonmisesmix()
,
qvonmisesmix()
.
Examples
set.seed(123)
n <- 10
angles <- rvonmisesmix(n,
mu = c(0, pi),
kappa = c(2, 1),
prop = c(0.4,0.6)
)
mle.vonmisesmix(theta = angles)
mle.vonmisesmix(theta = angles, mu = c(0, pi))