With thanks, as ever to Kit Baum, a new version of svylorenz is available on SSC. This version fixes a bug in the calculation of the standard errors for quantile group shares, and cumulative quantile group shares (Lorenz ordinates). See below for more details on the program.
I would like to acknowledge the help provided by Ben Jann. He alerted me to the bug and showed me how to fix it.
The SEs calculated by the previous version of the program were too large, so inference was too conservative (which at least is in the right direction!)
Estimates of shares and their standard errors can also be derived using Ben Jann's program pshare (on SSC), and svylorenz and pshare yield the same results. Each program has additional features not included in the other. For example, svylorenz calculates generalised Lorenz ordinates (calculation of their SEs was not affected by the bug), and provides an estimated SE for the Gini coefficient.
. ssc describe svylorenz
----------------------------------------------------------------------------------------------------------------------------------------------------
package svylorenz from http://fmwww.bc.edu/repec/bocode/s
----------------------------------------------------------------------------------------------------------------------------------------------------
TITLE
'SVYLORENZ': module to derive distribution-free variance estimates from complex survey data, of quantile group shares of a total, cumulative q
> uantile group shares
DESCRIPTION/AUTHOR(S)
svylorenz computes distribution-free variance estimates for
quantile group shares of a total, cumulative quantile group
shares, and the Gini coefficient, when estimated from complex
survey data. Note that the Gini coefficient is calculated using
all observations; it is not derived by approximation from the
income shares. svylorenz may also be used to draw Lorenz curves
(but see also glcurve).
KW: inequality
KW: Gini coefficient
KW: Lorenz
KW: Lorenz curve
Requires: Stata version 9
Distribution-Date: 20150915
Author: Stephen P. Jenkins, London School of Economics and Political Science
Support: email [email protected]
INSTALLATION FILES (type net install svylorenz)
svylorenz.ado
svylorenz.hlp
----------------------------------------------------------------------------------------------------------------------------------------------------
(type -ssc install svylorenz- to install)
I would like to acknowledge the help provided by Ben Jann. He alerted me to the bug and showed me how to fix it.
The SEs calculated by the previous version of the program were too large, so inference was too conservative (which at least is in the right direction!)
Estimates of shares and their standard errors can also be derived using Ben Jann's program pshare (on SSC), and svylorenz and pshare yield the same results. Each program has additional features not included in the other. For example, svylorenz calculates generalised Lorenz ordinates (calculation of their SEs was not affected by the bug), and provides an estimated SE for the Gini coefficient.
. ssc describe svylorenz
----------------------------------------------------------------------------------------------------------------------------------------------------
package svylorenz from http://fmwww.bc.edu/repec/bocode/s
----------------------------------------------------------------------------------------------------------------------------------------------------
TITLE
'SVYLORENZ': module to derive distribution-free variance estimates from complex survey data, of quantile group shares of a total, cumulative q
> uantile group shares
DESCRIPTION/AUTHOR(S)
svylorenz computes distribution-free variance estimates for
quantile group shares of a total, cumulative quantile group
shares, and the Gini coefficient, when estimated from complex
survey data. Note that the Gini coefficient is calculated using
all observations; it is not derived by approximation from the
income shares. svylorenz may also be used to draw Lorenz curves
(but see also glcurve).
KW: inequality
KW: Gini coefficient
KW: Lorenz
KW: Lorenz curve
Requires: Stata version 9
Distribution-Date: 20150915
Author: Stephen P. Jenkins, London School of Economics and Political Science
Support: email [email protected]
INSTALLATION FILES (type net install svylorenz)
svylorenz.ado
svylorenz.hlp
----------------------------------------------------------------------------------------------------------------------------------------------------
(type -ssc install svylorenz- to install)