nimbleSCR (version 0.2.1)

dHabitatMask: Ones trick distribution for irregular habitat shapes

Description

The dHabitatMask distribution checks and ensures that the proposed activity center location (s) falls within the suitable habitat (defined in the binary matrix habitatMask).

Usage

dHabitatMask(x, s, xmax, xmin, ymax, ymin, habitatMask, log = 0)
rHabitatMask(n, s, xmax, xmin, ymax, ymin, habitatMask)

Value

The log-likelihood value associated with the bivariate activity center location s being in the suitable habitat (i.e. 0 if it falls within the habitat mask and -Inf otherwise).

Arguments

x

Ones trick data.

s

Bivariate activity center coordinates.

xmax

Maximum of trap location x-coordinates.

xmin

Minimum of trap location x-coordinates.

ymax

Maximum of trap location y-coordinates.

ymin

Minimum of trap location y-coordinates.

habitatMask

A binary matrix object indicating which cells are considered as suitable habitat.

log

Logical argument, specifying whether to return the log-probability of the distribution.

n

Integer specifying the number of realisations to generate. Only n = 1 is supported.

Author

Daniel Turek

Details

The rHabitatMask function returns the value of the habitat mask cell (0 or 1) where the proposed activity center falls. See also M. Meredith: SECR in BUGS/JAGS with patchy habitat.

Examples

## define model code
code <- nimbleCode({
    for(i in 1:N) {
        s[i, 1] ~ dunif(0, 100)
        s[i, 2] ~ dunif(0, 100)
        OK[i] ~ dHabitatMask( s = s[i,1:2],
                              xmax = 100,
                              xmin = 0,
                              ymax = 100,
                              ymin = 0,
                              habitatMask = habitatMask[1:100,1:100])
    }
})
 
N <- 20
 
habitatMask <- matrix(rbinom(10000,1,0.75), nrow = 100)
 
constants <- list(N = N, habitatMask = habitatMask)
 
data <- list(OK = rep(1, N))
 
inits <- list(s = array(runif(2*N, 0, 100), c(N,2)))
 
## create NIMBLE model object
Rmodel <- nimbleModel(code, constants, data, inits)
 
## use model object for MCMC, etc.