Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
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/