# Re: st: Re: percentages (p75)

 From Maarten buis To cbaylor@ucla.edu Subject Re: st: Re: percentages (p75) Date Sat, 19 May 2007 07:50:32 +0100 (BST)

```Yes, and the principle is pretty much the same in the example I sent
earlier:
*-------------- begin example --------------
sysuse nlsw88, clear
xtile quintile = wage, nquantiles(5)

twoway kdensity tenure if quintile==1 || /*
*/  kdensity tenure if quintile==2 || /*
*/  kdensity tenure if quintile==3 || /*
*/  kdensity tenure if quintile==4 || /*
*/  kdensity tenure if quintile==5
*-------------- end example ----------------
(For more on how to use examples I sent to the Statalist, see:
http://home.fsw.vu.nl/m.buis/stata/exampleFAQ.html )

--- cbaylor@ucla.edu wrote:
> Is there a way to do a fiveway kdensity smoother, similar to below
> but with 5 differently colored lines?

> > --- cbaylor@ucla.edu wrote:
> > > Do you know how to take the "liberals" and view a histogram of
> > > only their income, and then superimpose it on the general
> > > population income?

> --- Maarten Buis wrote:
> > Histograms aren't really well suited for this, have a look at
> > -kdensity- like in the extension of the example I sent earlier:
> >
> > *-------------- begin example --------------
> > sysuse nlsw88, clear
> > sum tenure, detail
> > local top25 = r(p75)
> > replace wage = -wage /*just to make sure the
> > top 25 % of tenure measures something similar
> > to the bottom 25% of wage, you shouldn't do
> > this in you data*/
> > sum wage, detail
> > local bottom25 = r(p25)
> > gen liberal = tenure >`top25' & wage < `bottom25' /*
> > */ if !missing(tenure,wage)
> >
> > twoway kdensity grade if liberal || /*
> >     */ kdensity grade,  /*
> >     */ legend(label(1 "only liberals") /*
> >           */  label(2 "general population"))
> > *-------------- end example ----------------
> > (For more on how to use examples I sent to the Statalist, see:
> > http://home.fsw.vu.nl/m.buis/stata/exampleFAQ.html )

-----------------------------------------
Maarten L. Buis
Department of Social Research Methodology
Vrije Universiteit Amsterdam
Boelelaan 1081
1081 HV Amsterdam
The Netherlands

Buitenveldertselaan 3 (Metropolitan), room Z434

+31 20 5986715

http://home.fsw.vu.nl/m.buis/
-----------------------------------------

___________________________________________________________
Yahoo! Mail is the world's favourite email. Don't settle for less, sign up for