CorCompare function

Compares Correlation Matrices

This function compares two correlation matrices numerically and graphically.

CorCompare(cor1, cor2, labels1, labels2, method1, method2, ndigits = 4,
lty1 = 1, lty2 = 2, col1 = 1, col2 = 2, lwd1 = 1.1, lwd2 = 1.1,
cex.label = 1.1, cex.legend = 1.2, lwd.legend = 1.2, cex.cor = 1, ...)

Arguments

• cor1,cor2: two correlation matrices based on different estimation methods
• labels1, labels2: labels for the two estimation methods
• method1, method2: description of the estimation methods
• ndigits: number of digits to be used for plotting the numbers
• lty1, lty2, col1,col2, lwd1, lwd2, cex.label, cex.cor: other graphics parameters
• cex.legend, lwd.legend: graphical parameters for the legend
• ...: further graphical parameters for the ellipses

Details

The ellipses are plotted with the function do.ellipses. Therefore the radius is calculated with singular value decomposition.

Returns

No return value, creates a plot.

References

C. Reimann, P. Filzmoser, R.G. Garrett, and R. Dutter: Statistical Data Analysis Explained. Applied Environmental Statistics with R. John Wiley and Sons, Chichester, 2008.

Author(s)

Peter Filzmoser <P.Filzmoser@tuwien.ac.at > http://cstat.tuwien.ac.at/filz/

Examples

data(chorizon)
x=chorizon[,c("Ca","Cu","Mg","Na","P","Sr","Zn")]
op <- par(mfrow=c(1,1),mar=c(4,4,2,0))
R=robustbase::covMcd(log10(x),cor=TRUE)$cor
P=cor(log10(x))

CorCompare(R,P,labels1=dimnames(x)[[2]],labels2=dimnames(x)[[2]],
method1="Robust",method2="Pearson",ndigits=2, cex.label=1.2)
par(op)