Hi Andrija, As far as I understood, your problem comes from the density() function - the domains of myd and myd1 are different, which causes slightly shifted x values in the density() output.
A simple workaround (which you maybe already came up with): dens1 <- density(myd, from=-1, to=6) # force both densities on same domains, dens2 <- density(myd1, from=-1, to=6) # which facilitates drawing plot(range(dens1$x, dens2$x), range(dens1$y, dens2$y), type = "n") lines(dens1, col=1, lwd=4) lines(dens2, col=2, lwd=4, lty=2) polygon(dens1$x, pmin(dens1$y, dens2$y), col="grey") But doing so causes inelegant distribution tails... Maybe somebody will have a more elegant suggestion ? Pierrick Bruneau CRP Gabriel Lippmann On Wed, Mar 20, 2013 at 1:32 PM, andrija djurovic <djandr...@gmail.com>wrote: > Hi all. > > I would like to highlight overlapping regions of two densities and I could > not find a way to do it. > > Here is the sample code: > > myd <- c(2,4,5, 4,3,2,2,3,3,3,2,3,3,4,2,4,3,3,3,2,2.5, > 2, 3,3, 2.3, 3, 3, 2, 3) > myd1 <- myd-2 > plot(range(density(myd)$x, density(myd1)$x), range(density(myd)$y, > density(myd1)$y), type = "n") > lines(density(myd), col=1, lwd=4) > lines(density(myd1), col=2, lwd=4, lty=2) > > So, I am trying to highlight the region from 1 to 4, on x axis, taking the > minimum value of corresponding y values. > > I am aware of polygon function but don't know how to define correctly x and > y coordinate vectors for this function. > > Could someone help me to solve this? > > Thank in advance. > > Andrija > > [[alternative HTML version deleted]] > > ______________________________________________ > R-help@r-project.org mailing list > https://stat.ethz.ch/mailman/listinfo/r-help > PLEASE do read the posting guide > http://www.R-project.org/posting-guide.html > and provide commented, minimal, self-contained, reproducible code. > [[alternative HTML version deleted]] ______________________________________________ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
