rho_priors: Specify prior for the spatial autoregressive parameter and...
In estimateW: Estimation of Spatial Weight Matrices

rho_priors

R Documentation

Specify prior for the spatial autoregressive parameter and sampling settings

Description

Specify prior for the spatial autoregressive parameter and sampling settings

Usage

rho_priors(
  rho_a_prior = 1,
  rho_b_prior = 1,
  rho_min = 0,
  rho_max = 1,
  init_rho_scale = 1,
  griddy_n = 60,
  use_griddy_gibbs = TRUE,
  mh_tune_low = 0.4,
  mh_tune_high = 0.6,
  mh_tune_scale = 0.1
)

Arguments

`rho_a_prior`	Single number. Prior hyperparameter for the four-parameter beta distribution `betapdf`. Defaults to 1.
`rho_b_prior`	Single number. Prior hyperparameter for the four-parameter beta distribution `betapdf`. Defaults to 1.
`rho_min`	Minimum value for `\rho` (default: 0)
`rho_max`	Maximum value for `\rho` (default: 1)
`init_rho_scale`	For Metropolis-Hastings step the initial candidate variance (default: 1)
`griddy_n`	single integer number. Sets how fine the grid approximation is. Default value is 60.
`use_griddy_gibbs`	Binary value. Should griddy-Gibbs be used for `\rho` estimation? `use_griddy_gibbs=TRUE` does not work if `row_standardized_prior = FALSE` is specified in the `W` prior specification. if TRUE: griddy-Gibbs step for sampling `\rho`; if FALSE: tuned random-walk Metropolis-Hastings step
`mh_tune_low`	Lower bound of acceptance rate for Metropolis-Hastings tuning (used if `use_griddy_gibbs==FALSE`)
`mh_tune_high`	Upper bound of acceptance rate for Metropolis-Hastings tuning (used if `use_griddy_gibbs==FALSE`)
`mh_tune_scale`	Scaling factor for Metropolis-Hastings tuning (used if `use_griddy_gibbs==FALSE`)