Converts occurrence environmental data into the list format required by the Stan presence-only model. The function validates inputs and builds a data-adaptive prior on the niche centroid.
Arguments
- env_occ
Data frame or matrix of environmental values at presence points (rows = points, columns = environmental variables).
- eta
LKJ shape parameter for correlation matrix prior (default 1, uniform over correlation matrices).
- sigma_rate
Rate parameter for exponential prior on standard deviations (default 0.1).
Value
A named list suitable for passing to fit_niche or directly
to CmdStan. Contains:
- N_occ
Number of occurrence points
- P
Number of environmental dimensions
- occ
Occurrence data matrix
- mu_prior
Prior mean for centroid (data-adaptive, equal to column means of env_occ)
- sigma_prior
Prior SD for centroid (data-adaptive, equal to 10 times column SDs of env_occ)
- sigma_rate
Rate for exponential prior on sigma (default 0.1)
- eta
LKJ shape parameter (default 1, uniform over correlation matrices)
Examples
if (FALSE) { # \dontrun{
# Simulate some 2D environmental data
set.seed(42)
occ <- data.frame(
bio01 = rnorm(50, 20, 3), # annual mean temperature
bio12 = rnorm(50, 800, 100) # annual precipitation
)
# Prepare for Stan
stan_data <- prepare_niche_data(occ)
str(stan_data)
} # }