areal_wombling_bayesian: Bayesian Areal Wombling

In jlegewie/BoundaryDetection: Areal boundary detection in R

Description

areal_wombling_bayesian for Bayesian areal wombling (Lu and Carlin 2005).

Usage

areal_wombling_bayesian(formula, family, sp, phi = "leroux", threshold = NA,
  ...)

Arguments

formula	A formula for the covariate part of the model, using the same notation as for the lm() function. y ~ 1 estimates a model without covariates.
family	One of either 'binomial', 'gaussian' or 'poisson', which respectively specify a binomial likelihood model with a logistic link function, a Gaussian likelihood model with an identity link function, or a Poisson likelihood model with a log link function.
sp	Object of type SpatialPolygonsDataFrame (sf objects as converted)
phi	Conditional autoregressive (CAR) prior for the random effect. Options are 'leroux' for the CAR prior proposed by Leroux et al. (1999) (the default), 'IAR' for the intrinsic CAR, and 'BYM' for the BYM CAR proposed by Besag et al. (1991).
threshold	Threshold for the boundary membership value (BMV). If threshold is /codeNA (the default), /codeareal_wombling uses fuzzy wombling. If threshold is specified (any value between 0 and 1), /codeareal_wombling uses crisp wombling using threshold to determine boundary membership.
...	Arguments passed to estimation command including burnin, n.sample, thin, and parameters for various priors.

Details

By default, censusr downloads and recodes a selected set of variables. These variables include 100-300 commonly used measures from the

Value

Object of class carbayes from package CARbayes with two additions: First, additional element borders of class SpatialLinesDataFrame, which includes all border lines and the postior median estimates for the boundary likelihood value and the boundary membership value (boundary probability if threshold is defined). Second, sampes includes additional elements for the McMC samples of the boundary likelihood value and the boundary membership value.

jlegewie/BoundaryDetection documentation built on May 17, 2019, 7:28 p.m.