Fwiw, encoding magnitude in color is generally a bad idea. Using area(*not* radius) is also not great, but maybe it will work for you.
See here for some explanation: https://www.amazon.com/Visual-Display-Quantitative-Information/dp/0961392142/ref=sr_1_1?s=books&ie=UTF8&qid=1518092778&sr=1-1&keywords=Tufte Bert On Feb 7, 2018 11:13 PM, "greg holly" <mak.hho...@gmail.com> wrote: > Hi Dear all; > > I would like to create a plot for regression coefficients with each > independent variable (x) along the side and the phenotypes (y) across the > top (as given below). For each data point, direction and magnitude of > effect could be color and significance could be the size of the circle? Is > this possible? > > > I would greatly be appreciated your help. > > Thanks, > > Greg > > > > y1 y2 y3 y4 y5 y6 > x1 > x2 > x3 > x4 > x5 > x6 > x7 > x8 > x9 > x10 > x11 > x12 > x13 > x14 > x15 > x16 > x17 > . > . > > [[alternative HTML version deleted]] > > ______________________________________________ > R-help@r-project.org mailing list -- To UNSUBSCRIBE and more, see > 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 -- To UNSUBSCRIBE and more, see 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.