Statalist


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

RE: st: RE: lorenz curve


From   philippe van kerm <[email protected]>
To   "[email protected]" <[email protected]>
Subject   RE: st: RE: lorenz curve
Date   Thu, 22 Jan 2009 14:08:17 +0100

> -----Message d'origine-----
> De : [email protected] [mailto:owner-
> [email protected]] De la part de [email protected]
> Envoyé : Thursday, January 22, 2009 11:51 AM
> À : [email protected]
> Objet : Re: st: RE: lorenz curve
>
> Ok, but I have a problem.
>
> I have to construct a single graph whit Lorenz curve of varname, lorenz
> curve of varname where population are ordered in descending order of
> varname and a 45° line. To construct the Loren curve where population
> are ordered in descending order of varname I typed:
> glcurve var , lorenz
> gen minvar = 0-var
> glcurve  var , sortvar(minvar) lorenz gl(t) gl(s) then, for the
> "traditional" lorenz curve:
> glcurve7 var if area3==1, lorenz gl(t1) p(s2) and to have a single
> graph:
> line s t||function y=x||line t1 s2
>
> But in this way the graph show me the 45° line, but the traditional
> lorenz curve is now similar to that construct ordring population in
> descending order..so both up the 45° line.
> Would it can be the fail?

You inverted the ordinates in -line s t-. Should be

twoway  line t s ||function y=x||line t1 s2

Note in passing that you should also use -glcurve- (not -glcurve7-) for your 'traditional' curve too.

Philippe


*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/



© Copyright 1996–2024 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index