Dear all
I would like to represent the outliers in the plot. These few outliers are much larger than the limit of 50 in the ylim-argument.
plot(daten$month~daten$no,ylim=c(0,50))
I know that it is possible to introduce the information about the presence of outliers without changing the range of the axis. Do you have an advice? I hope the question is understandable!!
Three things come to mind --
1) Use a logarithmic y-axis.
2) Put text directly on the plot, stating where outliers are.
3) Use layout() and margin and axis settings of par() to stack two plots one above the other, with different y-ranges, like this:
## layout of a split-range plot
## fake data
zz <- runif(100,0,35) zz[sample(seq(along=zz),10)] <- runif(10,90,100)
par(mfcol=c(2,1)) par(mai=c(0, 1, 0.25,0.5)) plot(zz,ylim=c(80,100),xaxt="n",ylab="Outliers") par(mai=c(1,1,0,0.5)) plot(zz,ylim=c(0,50),ylab="Nice data")
Hope that helps
Jason
______________________________________________ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
