svywattsdec: Watts poverty index decomposition

In convey: Income Concentration Analysis with Complex Survey Samples

Watts poverty index decomposition

Description

Estimate the Watts (1968) poverty measure and its components

Usage

svywattsdec(formula, design, ...)

## S3 method for class 'survey.design'
svywattsdec(
  formula,
  design,
  type_thresh = "abs",
  abs_thresh = NULL,
  percent = 0.6,
  quantiles = 0.5,
  na.rm = FALSE,
  thresh = FALSE,
  ...
)

## S3 method for class 'svyrep.design'
svywattsdec(
  formula,
  design,
  type_thresh = "abs",
  abs_thresh = NULL,
  percent = 0.6,
  quantiles = 0.5,
  na.rm = FALSE,
  thresh = FALSE,
  return.replicates = FALSE,
  ...
)

## S3 method for class 'DBIsvydesign'
svywattsdec(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.
...	additional arguments. Currently not used.
type_thresh	type of poverty threshold. If "abs" the threshold is fixed and given the value of abs_thresh; if "relq" it is given by percent times the quantile; if "relm" it is percent times the mean.
abs_thresh	poverty threshold value if type_thresh is "abs"
percent	the multiple of the the quantile or mean used in the poverty threshold definition
quantiles	the quantile used used in the poverty threshold definition
na.rm	Should cases with missing values be dropped?
thresh	return the poverty threshold value
return.replicates	Return the replicate estimates?

Details

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

For the svywatts and svywattsdec functions, zeroes and negative numbers in the analysis domain cause an error because of the logarithm function in the definition of this poverty measure. However, zeroes and negative values in the full survey design that are outside of the domain of analysis are valid to calculate the poverty threshold because zeroes and negatives are not a problem for computing quantiles (used when type_thresh = "relq") or means (used when type_thresh = "relm") . Missing values are treated differently. NA values anywhere in the full survey design (not only the subset, or the domain of analysis) will cause these quantiles and means to return NA results. To ignore NA values throughout, set na.rm = TRUE.

Value

Object of class "cvydstat", with estimates for the Watts index, FGT(0), Watts Poverty Gap Ratio, and Theil(poor incomes) with a "var" attribute giving the variance-covariance matrix. A "statistic" attribute giving the name of the statistic.

Author(s)

Guilherme Jacob, Djalma Pessoa, and Anthony Damico

References

McKinley L. Blackburn (1989). Poverty measurement: an index related to a Theil measure of inequality. Journal of Business & Economic Statistics, Vol.7, No.4, pp. 475-481, DOI \Sexpr[results=rd]{tools:::Rd_expr_doi("10.1080/07350015.1989.10509760")}.

Satya R. Chakravarty, Joseph Deutsch and Jacques Silber (2008). On the Watts multidimensional poverty index and its decomposition. World Development, Vol.36, No.6, pp.1067-1077.

Harold W. Watts (1968). An economic definition of poverty. Institute For Research on Poverty Discussion Papers, n.5. University of Wisconsin. URL https://www.irp.wisc.edu/publications/dps/pdfs/dp568.pdf.

Guillaume Osier (2009). Variance estimation for complex indicators of poverty and inequality. Journal of the European Survey Research Association, Vol.3, No.3, pp. 167-195, ISSN 1864-3361, URL https://ojs.ub.uni-konstanz.de/srm/article/view/369.

Jean-Claude Deville (1999). Variance estimation for complex statistics and estimators: linearization and residual techniques. Survey Methodology, 25, 193-203, URL https://www150.statcan.gc.ca/n1/en/catalogue/12-001-X19990024882.

See Also

svywatts,svyfgt,svyfgt

Examples

library(survey)
library(laeken)
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 )

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

# filter positive incomes
des_eusilc <- subset( des_eusilc , eqincome > 0 )
des_eusilc_rep <- subset( des_eusilc_rep , eqincome > 0 )

# absolute poverty threshold
svywattsdec(~eqincome, des_eusilc, abs_thresh=10000)
# poverty threshold equal to arpt
svywattsdec(~eqincome, des_eusilc, type_thresh= "relq" , thresh = TRUE)
# poverty threshold equal to 0.6 times the mean
svywattsdec(~eqincome, des_eusilc, type_thresh= "relm" , thresh = TRUE)

#  using svrep.design:
# absolute poverty threshold
svywattsdec(~eqincome, des_eusilc_rep, abs_thresh=10000)
# poverty threshold equal to arpt
svywattsdec(~eqincome, des_eusilc_rep, type_thresh= "relq" , thresh = TRUE)
# poverty threshold equal to 0.6 times the mean
svywattsdec(~eqincome, des_eusilc_rep, type_thresh= "relm" , thresh = TRUE)

## Not run: 

# database-backed design
library(RSQLite)
library(DBI)
dbfile <- tempfile()
conn <- dbConnect( RSQLite::SQLite() , dbfile )
dbWriteTable( conn , 'eusilc' , eusilc )

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

dbd_eusilc <- convey_prep( dbd_eusilc )
dbd_eusilc <- subset( dbd_eusilc , eqincome > 0 )

# absolute poverty threshold
svywattsdec(~eqincome, dbd_eusilc, abs_thresh=10000)
# poverty threshold equal to arpt
svywattsdec(~eqincome, dbd_eusilc, type_thresh= "relq" , thresh = TRUE)
# poverty threshold equal to 0.6 times the mean
svywattsdec(~eqincome, dbd_eusilc, type_thresh= "relm" , thresh = TRUE)

dbRemoveTable( conn , 'eusilc' )

dbDisconnect( conn , shutdown = TRUE )


## End(Not run)

convey documentation built on Oct. 16, 2024, 5:10 p.m.