wiqid (version 0.3.3)

Bayesian SCR: Spatially explicit capture-recapture (secr) density estimation using MCMC

Description

Functions to estimate density from mark-recapture data using MCMC methods and JAGS.

Usage

Bsecr0(capthist, buffer = 100, start = NULL, nAug = NA, maxSig = 2*buffer,
                    chains=3, draws=1e4, burnin=0, thin=1, adapt=1000,
                    priorOnly=FALSE, parallel=NULL, seed=NULL, ...)

Value

Returns an object of class Bwiqid, data frame with one column for each parameter, ie. D, lam0 and sigma.

There are print, plot, and window methods for Bwiqid.

Arguments

capthist

a capthist object as defined in package secr including capture data and detector (trap) layout

buffer

scalar mask buffer radius (default 100 m)

start

an optional object of class secr, ie, output from the secr.fit function in package secr; objects of other classes are silently ignored.

nAug

number of individuals in the augmented population; if NA, a suitable default is chosen based on the object passed to start or a preliminary run of secr.fit.

maxSig

maximum value for the scale parameter of the detection function: the prior is Uniform(0, maxSig).

chains

the number of Markov chains to run.

draws

the total number of values to return. The number of values calculated per chain is adapt + burnin + ceiling(draws / chains) * thin.

burnin

the number of values to discard at the beginning of each chain.

thin

the thinning rate. If set to n > 1, n values are calculated for each value returned.

adapt

the number of iterations to run in the JAGS adaptive phase.

priorOnly

if TRUE, the function produces random draws from the appropriate prior distributions, with a warning.

seed

set a seed for the random number generators.

parallel

if TRUE or NULL and sufficient cores are available, the MCMC chains are run in parallel; if TRUE and insufficient cores are available, a warning is given.

...

other arguments to pass to the function.

Author

Mike Meredith

Details

Bsecr0 implements an intercept-only model (D ~ 1, g0 ~ 1, sigma ~ 1).

References

Borchers & Efford (2008) Spatially explicit maximum likelihood methods for capture-recapture studies Biometrics 64, 377-385

Royle & Dorazio (2008) Hierarchical Modeling and Inference in Ecology. Academic Press

See Also

The function secr.fit in package secr.

Examples

# \donttest{
if(requireNamespace("secr") && requireNamespace("rjags")) {
  # The stoats data set in 'secr'
  data(stoatDNA, package="secr")
  # This takes ca 10 mins on a multicore machine:
  Bout <- Bsecr0(stoatCH, buffer=1000, chains=2) # 2 chains for testing
  summary(Bout)
  plot(Bout)
  # look at diagnostic plots to see if D is constrained by nAug:
  diagPlot(Bout)      # Upper values of D doesn't look constrained.
  plotACs(Bout, 1:20) # Plot the ACs for captured animals
}
# }