Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down on April 23, and its replacement, statalist.org is already up and running.


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

Re: st: Multiple density plots, rotated and distributed on x-axis


From   Venable <venablito@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: Multiple density plots, rotated and distributed on x-axis
Date   Thu, 4 Aug 2011 16:11:45 -0400

Scott and Austin,

Both of those are extremely helpful, thank you both very much.

Scott's is a bit closer to what I had in mind but vioplot is quite
impressive as well.

On Tue, Aug 2, 2011 at 3:06 PM, Austin Nichols <austinnichols@gmail.com> wrote:
> Venable <venablito@gmail.com>:
> I love Scott's example, but see also -vioplot- on SSC:
> sysuse auto, clear
> vioplot mpg, over(foreign)
>
> On Tue, Aug 2, 2011 at 1:55 PM, Scott Merryman <scott.merryman@gmail.com> wrote:
>> Like this?
>>
>> clear
>> sysuse auto
>> set obs 5000
>> kdensity mpg if fore == 0, n(5000) k(gauss) bw(3) gen(h0 d0)
>> line d0 h0
>> kdensity mpg if fore == 1, n(5000) k(gauss) bw(3) gen(h1 d1)
>>
>> replace d1 = d1 + .2
>>
>> tabstat mpg, by(fore) stat(p25 p50 p75) nototal
>>
>> line h1 d1 || line h0 d0, xtitle("")  xlabel( .02 "Domestic" .22
>> "Foreign" ) ///
>>  legend(off)  scheme(lean1)   ///
>>  || scatteri  24.5 .264   19 .077 , recast(connected) ms(O) lw(thin)  ///
>>  || scatteri  21 .255   16.5 .0698 , recast(connected) ms(O) lw(thin) ///
>>  || scatteri  28 .2427   22 .0601 , recast(connected) ms(O) lw(thin)
>>
>>
>> Scott
>>
>>
>> On Mon, Aug 1, 2011 at 1:26 PM, Venable <venablito@gmail.com> wrote:
>>> Dear Statalist,
>>>
>>> I would like to create a graph that contains several kernel density
>>> plots, but with the plot rotated 90% right from the usual orientation,
>>> and with each plot aligned to a point on the x axis.
>>>
>>> To be more concrete (borrowing an example from Angrist and Pischke,
>>> Mostly Harmless Econometrics, Figure 3.1.1), suppose I wanted to show
>>> the distribution of incomes in the US at different levels of eduction,
>>> e.g. 8 years, 12 years, 14, 16, etc. The x-axis of the graph would be
>>> years of education and the y axis the level of income.  Above each
>>> year, there would be a kernel density plot of incomes for that year,
>>> with each rotated to the right, so that the "height" (density) is
>>> horizontal distance.
>>>
>>> An additional bonus would be to be able to mark a few quantiles on
>>> each density and connect these between years. For example, mark the
>>> 25th, median and 75th percentile for each year and have these points
>>> connected.
>>>
>>> Is this possible in Stata?
>>>
>>> I fear I may not be explaining this well in words, in spite of the
>>> fact that it is very easy to show as a picture. Unfortunately Figure
>>> 3.1.1 is not available in the Google Preview version of Mostly
>>> Harmless Econometrics, so I have posted a simple hand-drawn version
>>> here:
>>>
>>> http://dl.dropbox.com/u/2937392/density-plot-sketch.pdf
>
> *
> *   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/
>

*
*   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 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index