CorGroups function

Correlation Matrix for Sub-groups

The correlation matrix for sub-groups of data is computed and displayed in a graphic.

CorGroups(dat, grouping, labels1, labels2, legend, ndigits = 4,
method = "pearson", ...)

Arguments

• dat: data values (probably log10-transformed)
• grouping: factor with levels for different groups
• labels1, labels2: labels for groups
• legend: plotting legend
• ndigits: number of digits to be used for plotting the numbers
• method: correlation method: "pearson", "spearman" or "kendall"
• ...: will not be used in the function

Details

The corralation is estimated with a non robust method but it is possible to select between the method of Pearson, Spearman and Kendall. The groups must be provided by the user.

Returns

Graphic with the different sub-groups.

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")]

#definition of the groups
lit=chorizon[,"LITO"]
litolog=rep(NA, length(lit))
litolog[lit==10] <- 1
litolog[lit==52] <- 2
litolog[lit==81 | lit==82 | lit==83] <- 3
litolog[lit==7] <- 4
litolog <- litolog[!is.na(litolog)]
litolog <- factor(litolog, labels=c("AB","PG","AR","LPS"))

op <- par(mfrow=c(1,1),mar=c(0.1,0.1,0.1,0.1))
CorGroups(log10(x), grouping=litolog, labels1=dimnames(x)[[2]],labels2=dimnames(x)[[2]],
legend=c("Caledonian Sediments","Basalts","Alkaline Rocks","Granites"),ndigits=2)
par(op)