MixturePlot function

This function makes contour plots in the simplex mixture space.

This function makes contour plots in the simplex mixture space, it also can draw constraint lines and show design points.

MixturePlot(x=NULL,y=NULL,z=NULL,w=NULL,des=NULL,
                       res=400,lims=c(rep(0,6)),color.palette = heat.colors,
                       constrts=FALSE,contrs=TRUE,n.breaks=10,levels=NULL,
                       cols=FALSE, despts=TRUE, mod=NA,x3lab="Fraction X3",
                       x2lab="Fraction X2", x1lab="Fraction X1", 
                       corner.labs = NULL,
                       colorkey=list(dx=0.04,x0=0.95,y0=0.45,y1=0.90,add=TRUE,mode="all"),
                       pseudo=FALSE)

Arguments

• x: x3 locations for known points
• y: x2 locations for known points
• z: x1 locations for known points
• w: y locations for known points
• des: data frame with x1,x2,x3, and y locations for known points
• res: number of color blocks between 0 and 1 of x
• lims: vector of lower and upper constraints for x1,x2,x3
• color.palette: is the color palette to use
• constrts: if TRUE constraints found in lines will be added to the graph
• contrs: if TRUE contour lines will be added to the graph
• n.breaks: number of breaks between levels, this is used if levels is not specified
• levels: vector of contour levels to be plotted
• cols: if TRUE regions between contour lines will be colored
• despts: if TRUE plots the design points in data frame des
• mod: is an indicator for the model 1=linear, 2=quadratic, 4=special cubic. for other Models use the ModelEff function.
• x3lab: label for the x3 axis
• x2lab: label for the x2 axis
• x1lab: label for the x1 axis
• corner.labs: labels for x3, x2 and x1 vertices
• colorkey: a list with the location of the color key
• pseudo: if pseudo=TRUE uses pseudo components to zoom in on constrained region. By default pseudo=FALSE

References

1. Cornell, J. A. Experiments with Mixtures: Models and Analysis of Mixture Data, John Wiley & Sons, New York, third edition, 2002.

2. See R Ternary Level Plot Function http://www.siftp.net/index.shtml

3. "John Lawson, Cameron Willden (2016).", "Mixture Experiments in R Using mixexp.", "Journal of Statistical Software, Code Snippets, 72(2), 1-20." "doi:10.18637/jss.v072.c02"

Author(s)

John S. Lawson lawson@byu.edu

Examples

##Usage and Examples - Example from page 458 DAE with SAS
dat = data.frame(
          "x1"=c(1,.8,.6,.5,.5,.33333,.3,.3,.1,.1,0,0,0),
          "x2"=c(0,.1,.2,0,.5,.33333,.2,.5,.1,.8,0,.5,1),
          "x3"=c(0,.1,.2,.5,0,.33333,.5,.2,.8,.1,1.0,.5,0),
          "y"=c(48.7,49.5,50.2,52.8,49.3,51.1,52.7,50.3,60.7,49.9,64.9,53.5,50.6) 
                 )
MixturePlot(dat$x3,dat$x2,dat$x1,dat$y, x3lab="Fraction x3",
  x2lab="Fraction x2", x1lab="Fraction x1", corner.labs=c("x3","x2","x1"),
  constrts=FALSE,contrs=TRUE,cols=TRUE, mod=2,n.breaks=9)

# Weed control example from Lawson & Erjavec
x1<-c(1,0,0,.5,.5,0,.33333,.33333,.33333)
x2<-c(0,1,0,.5,0,.5,.33333,.33333,.33333)
x3<-c(0,0,1,0,.5,.5,.33333,.33333,.33333)
y<-c(73,68,80,77,86,75,92,93,88)
des<-data.frame(x1,x2,x3,y)
MixturePlot(des=des,x3lab="Fraction C",x2lab="Fraction B",
   x1lab="Fraction A",corner.labs=c("C","B","A"),mod=4,n.breaks=5,cols=TRUE)