Showing a distribution over time: how many summary stats?

August 13, 2015
By

(This article was first published on Robert Grant's stats blog » R, and kindly contributed to R-bloggers)

I saw this nice graph today on Twitter, by Thomas Forth:

but the more I looked at it, the more I felt it was hard to understand the changes over time across the income distribution from the Gini coefficient and the median. People started asking online for other percentiles, so I thought I would smooth each of them from the source data and plot them side by side:

uk_income

Now, this has the advantage of showing exactly where in society the growth or contraction is, but it loses the engaging element of the wandering nation across economic space (cf Booze Space; where do we end up? washed up on the banks of the Walbrook?), which should not be sneezed at. Something engaging matters in dataviz.

Code (as you know, I’m a nuts ‘n’ bolts guy, so don’t go recommending ggplot2 to me):


library(foreign)
library(splines)
bluecol<-"#467db4"
redcol<-"#b44f46"
uk<-read.csv("uk_income.csv")[1:53,1:22]
uk$Year <- as.numeric(substr(uk$Year,1,4))
sm<-apply(uk,2,function(z){smooth.spline(x=uk$Year,y=z)$y})
png("uk_income.png")
par(yaxs="i")
plot(uk$Year[1:3],sm[1:3,4],type="l",
ylim=c(min(sm[,4:22]-1),max(sm[,4:22]+60)),
xlim=c(1960,2015),
col=bluecol,
main="Percentiles of UK income over time",
sub="(Colour indicates governing political party)",
ylab="2013 GBP",
xlab="Year")
lines(uk$Year[4:10],sm[4:10,4],col=redcol) # Wilson I
lines(uk$Year[11:14],sm[11:14,4],col=bluecol) # Heath
lines(uk$Year[15:19],sm[15:19,4],col=redcol) # Wilson II, Callaghan
lines(uk$Year[20:37],sm[20:37,4],col=bluecol) # Thatcher, Major
lines(uk$Year[38:50],sm[38:50,4],col=redcol) # Blair, Brown
lines(uk$Year[51:53],sm[51:53,4],col=bluecol) # cameron
for(i in 5:22) {
lines(uk$Year[1:3],sm[1:3,i],col=bluecol) # Macmillan, Douglas-Home
lines(uk$Year[4:10],sm[4:10,i],col=redcol) # Wilson I
lines(uk$Year[11:14],sm[11:14,i],col=bluecol) # Heath
lines(uk$Year[15:19],sm[15:19,i],col=redcol) # Wilson II, Callaghan
lines(uk$Year[20:37],sm[20:37,i],col=bluecol) # Thatcher, Major
lines(uk$Year[38:50],sm[38:50,i],col=redcol) # Blair, Brown
lines(uk$Year[51:53],sm[51:53,i],col=bluecol) # Cam'ron
}
dev.off()

(uk_income.csv is just the trimmed down source data spreadsheet)

To leave a comment for the author, please follow the link and comment on their blog: Robert Grant's stats blog » R.

R-bloggers.com offers daily e-mail updates about R news and tutorials on topics such as: Data science, Big Data, R jobs, visualization (ggplot2, Boxplots, maps, animation), programming (RStudio, Sweave, LaTeX, SQL, Eclipse, git, hadoop, Web Scraping) statistics (regression, PCA, time series, trading) and more...



If you got this far, why not subscribe for updates from the site? Choose your flavor: e-mail, twitter, RSS, or facebook...

Comments are closed.

Search R-bloggers


Sponsors

Never miss an update!
Subscribe to R-bloggers to receive
e-mails with the latest R posts.
(You will not see this message again.)

Click here to close (This popup will not appear again)