This function allows the point estimates and confidence intervals of an initial estimated movement model to be improved by parametric boostrap, as described in Fleming et al (2018).
ctmm.boot(data,CTMM,method=CTMM$method,multiplicative=TRUE,robust=FALSE,error=0.01,
cores=1,trace=TRUE,...)Timeseries data represented as a telemetry object.
A ctmm movement-model object from the output of ctmm.fit containing the initial parameter estimates.
Fitting method(s) to use: "ML", "HREML", "pREML", "pHREML", or "REML". See "Description" below.
Removes multiplicative bias (rather than additive) bias from positive scale parameters like area.
Uses robust estimates of the average and covariation for debiasing. Useful when multiplicative=TRUE and yet parameters are near boundaries.
Relative standard error target for bootstrap ensemble estimates and nonlinear iterations.
Number of simulations to run in parallel. cores=NULL will use all cores, while cores<0 will reserve abs(cores).
Report progress updates. Can be among 0:2 with increasing detail.
Further arguments passed to ctmm.fit.
A model fit object with relatively unbiased estimates of home-range area, location variance, and autocorrelation timescales (and more accurate CIs than ctmm.fit).
ctmm.boot can leverage multiple estimators via the method argument (see ctmm.fit) and as described in Fleming et al (2018), though generally this is only useful if the specified estimators deviate substantially from each other realtive to the target error.