mpitb.set {mpitbR}

Set the specification of the Multidimensional Poverty Measurement and Analysis project

Description

Set the specification of the Multidimensional Poverty Measurement and Analysis project

Usage

mpitb.set(data, ...)

## S3 method for class 'survey.design2'
mpitb.set(data, indicators, ..., name = "unnamed", desc = "desc.")

## S3 method for class 'data.frame'
mpitb.set(data, indicators, ..., name = "unnamed", desc = "desc.")

Arguments

data

a "survey.design2"-class object where a complex survey design was previously specified. Can be a "data.frame" but it is coerced to "survey.design2" class assuming equal probabilities.

...

other arguments

indicators

a list or character vector containing the names of the indicators. If it is a list, the element represents the dimension which character vector with their corresponding indicators. At most 10 dimensions are allowed. The indicators should belong to columns names of 'data'. See Details below.

name

a character containing a desired specification of the project name. It also serves as an ID and it is recommended to use short names (at most 10 characters are permitted).

desc

a character containing a desired specification of the project description.

Details

The data passed to data argument assumes that the indicators columns is the deprivation matrix \mathbf{g}^0 = [g_{ij}^0], where g_{ij}^0 = 1 if the i-th person is deprived in the j-th indicator and g_{ij}^0 = 0 otherwise, for i = 1,\ldots,n and j = 1,\ldots,d. This argument should be a "survey.design2"-class object in which the complex survey design structure was previously specified using svydesign of survey package. If data is a "data.frame", it is coerced to a "survey.design2"-class object assuming equal probabilities, which is rarely used in household surveys.

These columns should not contain any missing value. For estimating the multidimensional poverty measures, the R survey package supports missing values for calculating the point estimation but it would not be able to calculate the standard error and, therefore, the confidence intervals.

The indicators argument should contain the names of indicators corresponding to the columns names in data. It is advisable to pass a list object where each element is the dimension and contain the character string with the indicators name because the package can calculate the nested equal weights automatically in the subsequent estimations. At most 10 dimensions are allowed. It can also be a character string. In this later case, if nested weights across dimensions is used, the user should be careful and specified later the corresponding weights by hand.

Finally, name and desc arguments are useful for identifying each MPI setting while working in a multidimensional poverty measurement and analysis project. Names with more than 10 characters are not allowed for tidiness purposes.

Value

"mpitb_set"-class object

Author(s)

Ignacio Girela

References

Alkire, S., Foster, J. E., Seth, S., Santos, M. E., Roche, J., & Ballon, P. (2015). Multidimensional poverty measurement and analysis. Oxford University Press.

Alkire, S., Roche, J. M., & Vaz, A. (2017). Changes over time in multidimensional poverty: Methodology and results for 34 countries. World Development, 94, 232-249. doi:10.1016/j.worlddev.2017.01.011

Suppa, N. (2023). mpitb: A toolbox for multidimensional poverty indices. The Stata Journal, 23(3), 625-657. doi:10.1177/1536867X231195286

See Also

mpitb.est function.

Examples

library(mpitbR)

data <- subset(syn_cdta, t==1)
data <- na.omit(data)

svydata <- survey::svydesign(id=~psu, weights = ~weight, strata = ~stratum, data = data)

indicators <- list(d1 = c("d_nutr","d_cm"),
                   d2 = c("d_satt","d_educ"),
                   d3 = c("d_elct","d_sani","d_wtr","d_hsg","d_ckfl","d_asst"))

set <- mpitb.set(svydata, indicators = indicators, name = "myname", desc = "pref. desc")