univ: Synthetic population dataset for Multivatiate Linear Mixed...

In mind: Multivariate Model Based Inference for Domains

Synthetic population dataset for Multivatiate Linear Mixed Model

Description

Synthetic population data frame containing the complete list of the units belonging to the target population along with the corresponding values of the auxiliary variables.

Usage

data(univ)

Format

A data frame with 514320 observations on 7 variables:

dom

domain of interest codes

sexage

cross classification of age and sex

edu

educational level

fore

bynary variable, 2 for foreigner 1 otherwise

mun

municipal codes

pro

provincial codes

tot

column of 1

Details

The informations on the population are the same collected in the syntethic sample data_s appart from the information on the occupational status that are present only for the sample units.

mind.unit allows to use a data frame of known population totals based on the marginal distribution of the profile identified by the auxiliary variables (See 'Examples').

Examples

library(dplyr)

# Load example data
data(data_s);data(univ)
summary(univ)


formula<-as.formula(occ_stat~(1|pro)+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[,-5]

# 1) Estimation using the complete list of the unit beloging the target population:
example.1<-mind.unit(formula=formula,dom="dom",data=data_s,universe=univ_1)
rm(univ_1)

# Creation of the know population totals object:
univ_ag<-aggregate(tot~-1+factor(dom)+factor(pro)+
factor(sexage)+factor(edu)+factor(fore),univ,sum)
colnames(univ_ag)<-c("dom","pro","sexage","edu","fore","tot")

# Set all variables as numeric.
#Remember that only the domains codes and the random terms must to be numeric variables.
univ_ag <- mutate_all(univ_ag, function(x) as.numeric(as.character(x)))

# 2) Estimation using the know population totals (totals in univ_ag) :
example.2<-mind.unit(formula=formula,dom="dom",data=data_s,universe=univ_ag)

mind documentation built on Oct. 29, 2022, 1:09 a.m.