Distributive Analysis Stata Package (DASP)

Estimates inequality  indices and theirs standard errors taking full account of survey design.

- Gini index.
- Absolute Gini index.
- Concentration index.
- Absolute concentration index.
- Atkinson index.
- Generalised entropy index.
- Coefficient of variation index.
- Quantile ratio index.
- Share ratio index.

Estimates the polarisation indices and theirs standard errors taking full account of survey design.

- Duclos Esteban and Ray index of polarization (2004).
- Foster and Wolfson (1992).
- Esteban, Gradin and Ray (1999).
- INaki Permanyer (2008).

Estimates the poverty indices and their standard errors taking full account of survey design.

- FGT index.
- Normalised FGT index.
- EDE-FGT indices.
- Normalised EDE-FGT index.
- Watts poverty index.
- Sen-Shorrocks-Thon poverty indices.

- Chakravarty, Mukherjee, and Ranade (1998) MD poverty index.
- Extended Watts MD Poverty Index.
- Multiplicative FGT index.
- Tsui_2002 index.
- Intersection MD Poverty Index.
- Union Headcount MDl Poverty Index.
- Bourguignon and Chakravarty_2003 MD Poverty Index.
- Alkire and Foster (2011) MD Poverty Index.

The imoda DASP module produces a series of multidimensional poverty indices in order to show the incidence of deprivation in each dimension. Further, this application estimates the incidence of multi-deprivation in the different combinations of dimensions.
 

IPROPOOR

To estimate FGT pro-poor indices and its standard error taking full account of survey design. Indices are:

[1] Chen and Ravallion index (2003);
[2] Kakwani & Pernia (2000) index ;
[3] Kakwani, Khandker and Son (2003) -PEGR- index.

GICUR

To draw the growth incidence curve and its confidence interval.

CPROPOORP

To estimate absolute and relative pro-poor curves with the primal approach.

Detailed description:

Let the following notation:

Q(p) : quantile at percentile p.
GL(p) : generalised Lorenz at percentile p.
mu : average income.

[1] First-order absolute pro-poor curves
Select one of the two curves:

DELTA(p) = Q_2(p) - Q_1(p)
Or
DELTA(p) = ( Q_2(p) - Q_1(p) ) / Q_1(p)


[2] Second-order absolute pro-poor curves

Select one of the two curves:

DELTA(p) = GL_2(p) - GL_1(p)
Or
DELTA(p) = ( GL_2(p) - GL_1(p) ) /GL_1(p)

[3] First-order relative pro-poor curves
Select the curve:

DELTA(p) = Q_2(p)/Q_1(p) - mu_2/mu_1

[4] Second-order relative pro-poor curves

Select the curve:

DELTA(p) = GL_2(p)/GL_1(p) - mu_2/mu_1

EFGTGR

FGT-Elasticity with respect to growth in average income (Kakwani (1993)).

EFGTINEQ

FGT-Elasticity with respect to Gini inequality (Kakwani (1993)).

EFGTG

FGT-Elasticity with respect to the within/between group components of inequality.

EFGTC

FGT-Elasticity with respect to the within/between income components of inequality.

ITARGETG

The module itargetg produces the following estimates and curves for a given list of population groups:

• Impact of targeting population groups on FGT indice

• Impact of targeting population groups on FGT curves (along an axis of poverty lines)

• The confridence interval of the impact of targeting population groups on FGT curves (along an axis of poverty lines).

OGTPR

Poverty and targeting by population groups with a fixed budget.

ITARGETG2D

Bi-dimensional poverty and targeting by population groups.

ITARGETC

The module itargetc produces the following estimates and curves for a given list of population groups:

• Impact of targeting welfare components on FGT indice;

• Impact of targeting welfare components on on FGT curves (along an axis of poverty lines);

• The confidence interval of targeting welfare components on FGT curves (along an axis of poverty lines).

DFGTG

Decomposes FGT poverty indices by groups and provides standard errors on various elements of the decompositions.

1. The Datt and Ravallion approach (1991).
2. The Shapley approach.

1. The Jallan and Ravallion (1998) approach.
2. The Duclos, Araar and Giles (2006) approach.

The command dfgts decomposes the allevation of FGT poverty by income components and provides standard errors on elements of the decompositions. Without any source, the FGT index equals 1. The decomposition is performed using the Shapley value.

1. The Rao's approach (1969);
2. The Lerman and Yitzhaki approach (1985);
3. The Araar approach (2006).

The command rbdineq use the regression based decomposition approach to decompose inequality indices by income covariates.
The decomposition is performed using the Shapley value or the analytical approach. With the Shapley approach, the user can
select among the following inequality indices:

• Gini
• Atkinson
• Coefficient of variation
• Generalised entropy

Decomposes Alkire and Foster (2007) multidimensional poverty indices by groups and provides standard errors on various elements of the decompositions.

DOMPOV

To test the poverty dominance and to estimate the critical values (values for witch the two dominance curves cross) .

DOMINEQ

To test the inequality dominance based on Lorenz curves and to estimate the critical values (percentile values for witch the two Lorenz curves cross).

DOMBDPOV

To estimate the differences between bi-dimensional multiplicative FGT poverty (BD-FGT) surfaces with confidence interval.

CLORENZ

Produces the following curves and theirs confidence intervals for a given list of variables:

• Lorenz curves;

• Generalized Lorenz curves;

• Absolute Lorenz curves;

• Concentration curves;

• Generalized concentration curves;

• Absolute concentration curves;

• Deficit share curves;

• Differences between curves.

DICLORENZ

Produces the difference between the following curve with confidence interval

• (Generalized) Lorenz curves;

• (Generalized) Concentration curves.

Produces the following curves and theirs confidence intervalsfor a given list of variables:

• Normalised FGT curves;

• FGT curves.

DICFGT

Produces the difference between the following curve with confidence interval

• Normalised FGT curves;

• FGT curves.

Produces the following curves for a given list of variables:

• Poverty gap curves;

• Cumulative poverty curves.

CDOMC

Produces the following curve with confidence interval

• Normalised consumption dominance curves;

• Consumption dominance curves.

CDOMC2D

Produces the difference between the following curve with confidence interval

• Normalised consumption dominance curves;

• Consumption dominance.

CPROG

Let x be a gross income.
. A tax t is Tax Redistribution (TR) progressive if:
. PR(p) = L_x(p) - C_t(p) > 0 for all p in ]0, 1[

. A transfer b is Tax Redistribution (TR) progressive if:
. PR(p) = C_b(p) - L_x(p) > 0 for all p in ]0, 1[

. A tax t is Income Redistribution (IR) progressive if:
. PR(p) = C_x-t(p) - L_x(p) > 0 for all p in ]0, 1[

. A transfer b is Income Redistribution (IR) progressive
. PR(p) = C_x+b(p) - L_x(p) > 0 for all p in ]0, 1[
 

CPROGBT

Let x be a gross income.
. A transfer B is more Tax Redistribution (TR) than the tax T if:
. PR(p) = C_b(p) + C_t(p)- 2L_x(p) > 0 for all p in ]0, 1[


. A transfer B is more Income Redistribution (IR) than the tax T if:
. PR(p) = C_x+b(p) - C_x-t(p) > 0 for all p in ]0, 1[

CDENSITY

Produces the density curves

C_QUANTILE

Produces the following curves for a given list of variables:

• Quantile curves;

• Normalised quantile curves;

QUINSH

Estimate the income shares and cumulative income shares by group quantiles (quartiles/quintiles/deciles/etc.). Graph bar of income shares can be plotted.

CNPE

Produces the following curves for a given list of variables:

• Non parametric regression curves;

• Non parametric derivative regression curves;

SJDENSITY

Produces a bidimensional joint density in the form of a surface. The Gaussian kernel approach is used to estimate that density.

SJDISTRUB

Produces a joint distribution function in the form of a two-dimensional surface.

BIAN

Produces statistics based on the Benefit Incidence Analysis

IMBI

Marginal benefit incidence analysis

UNGROUP

The command ungroup generates disaggregated data using information on the aggregated data and on the form of the distribution to be assumed.