IC2 (version 1.0-1)

decompGEI: Decomposition by Groups for GEI

Description

Decomposes by population subgroups a generalized entropy inequality measure within a vector.

Usage

decompGEI(x, z, w = NULL, alpha = 1, ELMO = TRUE)

Arguments

x

Numeric vector with non-negative values (strictly positive when alpha=0 or alpha=1).

z

Factor who determines the subgroups.

w

Numeric vector of sampling weigths (optional).

alpha

Parameter of the generalized entropy index. Theil index ($TT$) is calculated for alpha=1, the mean log deviation ($TL$) for alpha=0.

ELMO

When ELMO is TRUE, a "maximum" between-group inequality index is estimated using the Elbers and alii method (2005).

Value

A list of class "ICI" with components:

ineq

a list with components GEI (value of inequality index) and alpha (value of parameter).

decomp

a list with components within (value of within-group inequality), between (value of between-group inequality) and, if ELMO is TRUE, betweenELMO (value of maximum between-group inequality).

intra

a list with components GEIGroups (the subgroup values of inequality index) and contribGEIGroups (the contribution of each subgroup to the total within-groups inequality).

ws

a list with components wIntra (the subgroup weights) and sIntra (the subgroup shares of x).

nas

a list with NA counts, including components xNA, zNA, wNA and totalNA.

References

Cowell F.A. (2000) Measurement of Inequality. In Atkinson A.B., Bourguignon F. (Eds.) Handbook of Income Distribution. Elsevier, Vol. 1, pp. 87-166.

Elbers C., Lanjouw P., Mistiaen J.A., Ozler B. (2005) Re-Interpreting Sub-Group Inequality Decompositions. World Bank, World Bank Policy Research Working Paper 3687, 42 p.

See Also

calcGEI

Examples

data(hhbudgets)

decompGEI(hhbudgets[,"ingreso"], hhbudgets[,"estructura"], alpha=4)
summary(hhbudgets[,"tenencia"]) #35 NA's
decompGEI(x=hhbudgets[,"transporte"], z=hhbudgets[,"tenencia"], w=hhbudgets[,"factor"], ELMO=FALSE)
summary(decompGEI(x=hhbudgets[,"transporte"], z=hhbudgets[,"tenencia"], w=hhbudgets[,"factor"], alpha=1.5))