BayesSAE: Univariate hierarchical Bayes approach to small area...

In ssoro411/bayesae: Hierarchical Bayes Spatial Models for Small Area Estimation

Description

Hierarchical Bayes approach to small area estimation using stan.

Arguments

formula	formula
data	Data frame with direct estimate and auxiliary variables.
Di	m vector with sampling variance.
domain	Vector with Domain names.
model	There are three possible models. "FH" for Fay-Herriot model, "CAR" for conditional auto-regressive model and "SAR" for simultaneous auto-regressive model.
W	Spatial matrix. If model="SAR", rowsum should be 1.
logit.trans	If true, it transforms direct estimate to logit scale and sampling variance is approximated by the delta mehod. Simulation result will be returned in origial proportion scale.
pars	Parameters to be monitored.
iter	Total iteration.
warmup	Warm up. Default is "floor(iter/2)".
chains	Number of chains. Default is 4.
control	See the rstan package document.
open.progress	Progress of chiain will be presented if it is TRUE.

Value

Simulated posterior sample from the rstan.

References

\insertRef

carpenter2016stanbayesae

\insertRef

guo2016rstanbayesae

\insertRef

vehtari2014waicbayesae

ssoro411/bayesae documentation built on Dec. 4, 2019, 3:03 p.m.