smoothUnit: Smooth via unit level model

In SUMMER: Small-Area-Estimation Unit/Area Models and Methods for Estimation in R

Smooth via unit level model

Description

Generates small area estimates by smoothing direct estimates using a unit level model

Usage

smoothUnit(
  formula,
  domain,
  design,
  family = c("gaussian", "binomial")[1],
  Amat = NULL,
  X.pop = NULL,
  domain.size = NULL,
  pc.u = 1,
  pc.alpha = 0.01,
  pc.u.phi = 0.5,
  pc.alpha.phi = 2/3,
  CI = 0.95,
  n.sample = 250
)

Arguments

formula	an object of class "formula" describing the model to be fitted.
domain	formula specifying variable containing domain labels
design	an object of class "svydesign" containing the data for the model
family	of the response variable, currently supports 'binomial' (default with logit link function) or 'gaussian'.
Amat	Adjacency matrix for the regions. If set to NULL, the IID spatial effect will be used.
X.pop	unit-level covariates data frame. One of the column name needs to match the domain specified, in order to be linked to the data input. Currently only supporting time-invariant domain-level covariates.
domain.size	Domain size data frame. One of the column name needs to match the domain specified, in order to be linked to the data input and there must be a size column containing domain sizes.
pc.u	hyperparameter U for the PC prior on precisions.
pc.alpha	hyperparameter alpha for the PC prior on precisions.
pc.u.phi	hyperparameter U for the PC prior on the mixture probability phi in BYM2 model.
pc.alpha.phi	hyperparameter alpha for the PC prior on the mixture probability phi in BYM2 model.
CI	the desired posterior credible interval to calculate
n.sample	number of draws from posterior used to compute summaries

Value

A list with elements

direct.est	direct estimates
model.fit	fitted INLA object for iid domain effects model
model.est	smoothed estimates

Examples

## Not run: 
library(survey)
data(DemoData2)
data(DemoMap2)
des0 <- svydesign(ids = ~clustid+id, strata = ~strata,
                 weights = ~weights, data = DemoData2, nest = T)
                 
EXAMPLE 1: Continuous response model
cts.res <- smoothUnit(formula = tobacco.use ~ 1,
                      domain = ~region,
                      design = des0, X.pop = DemoData2)
                      
EXAMPLE 2: Binary response model
bin.res <- smoothUnit(formula = tobacco.use ~ 1,
                      family = "binomial",
                      domain = ~region,
                      design = des0, X.pop = DemoData2)

## End(Not run)

SUMMER documentation built on July 8, 2022, 9:05 a.m.