I have some data for which, at one level of a factor, there is a significant correlation. At the other level, there is none. Plotting these side-by-side is simple. Adding a l
Of course, I later answered my own question. Although, is there a less hack-y way to do this? I wonder if one could even fit different functions to different panels.
One technique is to use + scale_fill_manual and scale_colour_manual. They allow one to specify what colors will be used. So, in this case, let's say you have
a<-qplot(x, y, facets=~z)+stat_smooth(method="lm", aes(colour=z, fill=z))
You can specify colors for the fill and colour using the following. Note, the second color is clear, as it is using a hex value with the final two numbers representing transparency. So, 00=clear.
a+stat_fill_manual(values=c("grey", "#11111100"))+scale_colour_manual(values=c("blue", "#11111100"))