mnllCRW: Maximum likelihood estimation of the CRW

In MarieAugerMethe/CCRWvsLW: Searching strategy movement models

Description

Minimize the negative log-likelihood for the CRW.

Usage

mnllCRW(SL, TA_C, TA, SLmin, lambda=(1/mean(SL-SLmin)))
nllCRW(SL,TA,kapp,lambda=parF$lambda,parF=list('SLmin'=min(SL)))

Arguments

SL	numeric vector containing the step lengths
TA	numeric vector containing the turning angles
TA_C	circular object containing the turning angles
SLmin	one numeric value representing the minimum step length
lambda	one numeric value for lambda, the default is the analytical solution
kapp	one numerci value for parameter
parF	list for fix parameter values, see default

Details

The mnllCRW function minimizes the negative log likelihood for the CRW. It uses the value the analytical solution that is the input for lambda and gets the MLE for kappa using the mle.vonmises function of the package circular.

The nllCRW function evaluates the negative log likelihood value.

References

Please refer to Auger-Methe, M., A.E. Derocher, M.J. Plank, E.A. Codling, M.A. Lewis (2015-In Press) Differentiating the Levy walk from a composite correlated random walk. Methods in Ecology and Evolution. Preprint available at http://arxiv.org/abs/1406.4355

Examples

simPath <- simmCRW(500,0.1,5,1)
formPath <- movFormat(simPath)
mnllCRW(formPath$SL, formPath$TA_C, formPath$TA, formPath$SLmin)

MarieAugerMethe/CCRWvsLW documentation built on May 7, 2019, 2:50 p.m.