mind (version 1.1.0)

benchSAE: Benchmark for SAE

Description

Benchmarked values based on ratio adjustment of the SAE estimates

Usage

benchSAE(estim_sae,benchmark_area,area,name_dom,estimator,Nest)

Value

benchSAE produces a data.frame with a column of domain indicator and set of columns (as specified in estimator) of benchmarked point predictions.

Arguments

estim_sae

a data frame containing the arguments area, name_dom, estimator and Nest

benchmark_area

a data frame identifing the area to be benchmarked among with the benchmark value

area

character, identified the name of the area to be benchmarked

name_dom

character, identified the name of the domains

estimator

vector, contain the name of the estimates to be benchmarked

Nest

character, identified the name of the total population size for domain

Author

Developed by Michele D'Alò

Details

The benchSAE function allows (i) to benchmark more than one SAE estimates at times and (ii) to specified the broadarea to be benchmarked, from the national level to a more disaggregated level.

References

Datta,G. S., Ghosh, M., Steorts, R. and Maples, J. (2010) Bayesian benchmarking with applications to small area estimation. Test, 20, 574–588.

Examples

# Load example data

data(data_s);data(univ)
# \donttest{
tot<-aggregate(tot~dom+pro,univ,sum)
  
# One random effect at domain level


  formula<-as.formula(cbind(emp,unemp,inact)~(1|mun)+
                        factor(sexage)+factor(edu)+factor(fore))
  
# Drop from the universe data frame variables not referenced in the formula or in the broadarea

  univ_1<-univ[,-6]

# Estimate mind model benchmarking the unemployment variable

  example.1<-mind.unit(formula=formula,dom="dom",data=data_s,universe=univ_1,MSE=FALSE)
  SAEest<-example.1$EBLUP[,c(1,3)]
  SAEest<-merge(SAEest,tot)
  SAEest$unemp<-SAEest$unemp/SAEest$tot
  bench<-data.frame(pro=c(10,11),bb=c(0.27,0.31))
  
# Benchmark the unemployment point estimates
  
  SAEest_bench<-benchSAE(estim_sae=SAEest,
                          benchmark_area=bench,
                          area="pro",
                          name_dom="dom",
                          estimator="unemp",
                          Nest="tot")
# }