Fit binomial model using Polya-Gamma Gibbs sampling
Usage
fit_pg_binomial(
formula,
data,
family,
spatial = NULL,
temporal = NULL,
iter = 2000,
warmup = floor(iter/2),
chains = 4,
thin = 1,
cores = NULL,
seed = NULL,
prior_beta_sd = 10,
prior_sigma_scale = 2.5,
prior_tau_shape = 1,
prior_tau_rate = 0.01,
verbose = TRUE
)Arguments
- formula
A ratiod_formula object
- data
Data frame
- family
Must be ratiod_binomial()
- spatial
Optional spatial structure from spatial_car() or spatial_bym2()
- iter
Total iterations per chain
- warmup
Warmup iterations per chain
- chains
Number of chains to run
- thin
Thinning interval
- cores
Number of cores for within-chain parallelism
- seed
Random seed for reproducibility
- prior_beta_sd
Prior SD for fixed effects (default 10)
- prior_sigma_scale
Half-Cauchy scale for RE SD (default 2.5)
- prior_tau_shape
Gamma shape for spatial precision (default 1)
- prior_tau_rate
Gamma rate for spatial precision (default 0.01)
- verbose
Print progress