svyjdiv: J-divergence measure (EXPERIMENTAL)

Description

Estimate the j-divergence measure, an entropy-based measure of inequality

Usage

svyjdiv(formula, design, ...)
# S3 method for survey.design
svyjdiv(formula, design, na.rm = FALSE, ...)
# S3 method for svyrep.design
svyjdiv(formula, design, na.rm = FALSE, ...)
# S3 method for DBIsvydesign
svyjdiv(formula, design, ...)

Arguments

formula

a formula specifying the income variable

design

a design object of class survey.design or class svyrep.design from the survey library.

...

future expansion

na.rm

Should cases with missing values be dropped?

Value

Object of class "cvystat", which are vectors with a "var" attribute giving the variance and a "statistic" attribute giving the name of the statistic.

Details

you must run the convey_prep function on your survey design object immediately after creating it with the svydesign or svrepdesign function.

This measure only allows for strictly positive variables.

References

Nicholas Rohde (2016). J-divergence measurements of economic inequality. J. R. Statist. Soc. A, v. 179, Part 3 (2016), pp. 847-870. URL http://onlinelibrary.wiley.com/doi/10.1111/rssa.12153/abstract.

Martin Biewen and Stephen Jenkins (2002). Estimation of Generalized Entropy and Atkinson Inequality Indices from Complex Survey Data. DIW Discussion Papers, No.345, URL https://www.diw.de/documents/publikationen/73/diw_01.c.40394.de/dp345.pdf.

Examples

Run this code

# NOT RUN {
library(survey)
library(vardpoor)
data(eusilc) ; names( eusilc ) <- tolower( names( eusilc ) )

# linearized design
des_eusilc <- svydesign( ids = ~rb030 , strata = ~db040 ,  weights = ~rb050 , data = eusilc )
des_eusilc <- convey_prep(des_eusilc)

svyjdiv( ~eqincome , design = subset( des_eusilc , eqincome > 0 ) )

# replicate-weighted design
des_eusilc_rep <- as.svrepdesign( des_eusilc , type = "bootstrap" )
des_eusilc_rep <- convey_prep(des_eusilc_rep)

svyjdiv( ~eqincome , design = subset( des_eusilc_rep , eqincome > 0 ) )

# }
# NOT RUN {
# linearized design using a variable with missings
svyjdiv( ~py010n , design = subset( des_eusilc , py010n > 0 | is.na( py010n ) ) )
svyjdiv( ~py010n , design = subset( des_eusilc , py010n > 0 | is.na( py010n ) ), na.rm = TRUE )
# replicate-weighted design using a variable with missings
svyjdiv( ~py010n , design = subset( des_eusilc_rep , py010n > 0 | is.na( py010n ) ) )
svyjdiv( ~py010n , design = subset( des_eusilc_rep , py010n > 0 | is.na( py010n ) ) , na.rm = TRUE )

# database-backed design
library(MonetDBLite)
library(DBI)
dbfolder <- tempdir()
conn <- dbConnect( MonetDBLite::MonetDBLite() , dbfolder )
dbWriteTable( conn , 'eusilc' , eusilc )

dbd_eusilc <-
	svydesign(
		ids = ~rb030 ,
		strata = ~db040 ,
		weights = ~rb050 ,
		data="eusilc",
		dbname=dbfolder,
		dbtype="MonetDBLite"
	)

dbd_eusilc <- convey_prep( dbd_eusilc )

svyjdiv( ~eqincome , design = subset( dbd_eusilc , eqincome > 0 ) )

dbRemoveTable( conn , 'eusilc' )

dbDisconnect( conn , shutdown = TRUE )

# }
# NOT RUN {
# }

Run the code above in your browser using DataCamp Workspace