ellipse
contains ellipse drawing routines designed for
pairwise confidence regions, including distorted ellipses for nonlinear
regression regions. It also includes a routine plotcorr()
for plotting correlation matrices using ellipses.
It is on CRAN, and can be installed using
install.packages("ellipse")
You can install the development version of ellipse from GitHub with:
# install.packages("devtools")
::install_github("dmurdoch/ellipse") devtools
Plot approximate pairwise confidence regions and profile trace plots for a nonlinear fit:
data(Puromycin)
<- nls(formula = rate ~ ((Vm + delV * (state == "treated"))
Purboth * conc)/(K + conc), data = Puromycin,
start = list(Vm = 160, delV = 40, K = 0.05))
<- profile(Purboth)
Pur.prof ::pairs(Pur.prof) ellipse
The plotcorr()
function can plot a matrix of
ellipses:
library(ellipse)
#>
#> Attaching package: 'ellipse'
#> The following object is masked from 'package:graphics':
#>
#> pairs
<- cor(mtcars)
corr.mtcars <- order(corr.mtcars[1,])
ord <- corr.mtcars[ord, ord]
xc <- c("#A50F15","#DE2D26","#FB6A4A","#FCAE91","#FEE5D9","white",
colors "#EFF3FF","#BDD7E7","#6BAED6","#3182BD","#08519C")
plotcorr(xc, col=colors[5*xc + 6])