This function estimates the mean value of an annotated covariate as a function of location, using non-parametric regression.

npr(data,UD,variable="speed",normalize=FALSE,debias=TRUE,error=0.001,...)

Arguments

data

2D timeseries telemetry data represented as a telemetry object or list of objects.

UD

A UD object from the output of akde.

variable

Variable for mean estimation. Can be a column of data.

normalize

Consider variable as providing a weighted probability distribution.

debias

Correct for oversmoothing if normalize=TRUE.

error

Target probability error.

...

Arguments passed to akde.

Value

Returns a UD object.

Author

C. H. Fleming.

See also

Examples

# \donttest{
# Load package and data
library(ctmm)
data(buffalo)
DATA <- buffalo$Cilla

# calculate fit guess object
GUESS <- ctmm.guess(DATA,interactive=FALSE)
# in general, you should be running ctmm.select here instead of ctmm.fit
FIT <- ctmm.fit(DATA,GUESS)

# Compute akde object
UD <- akde(DATA,FIT)
#> Default grid size of 3 minutes chosen for bandwidth(...,fast=TRUE).

# compute revisitation distribution
RD <- revisitation(DATA,UD)

# Plot data with revisitation distribution
plot(DATA,RD)
#> DOP values missing. Assuming DOP=1.

# }