# Extract a single 2 by 2 covariance matrix `covmat` extracts a 2 by 2 covariance matrix for one data point on two dimensions, allowing the confidence ellipse to be plotted ```r covmat(x, i, thing = "column", axis1 = 1, axis2 = 2, show = TRUE) ``` ## Arguments - `x`: An object of class `cabootcrsresults` - `i`: The number of the row or column, note that in MCA this will be the number of the variable category (e.g. for p=3 variables with 5 categories each, column 8 is the 3rd category of the 2nd variable) - `thing`: Whether to extract the covariance matrix for the i-th - **"row"**: row, or - **"column"**: column Note that default is "column" as this is more convenient for MCA - `axis1`: First axis for which (co)variances are required - `axis2`: Second axis for which (co)variances are required - `show`: If TRUE then print the extracted covariance matrix ## Returns An object of class `"matrix"` (square symmetric, 2 by 2) ## Details This can be used with the ellipse() package to add the confidence ellipse to a picture from another package Example: confidence ellipse for row or column i on axes 1,2 from cabootcrs() output Results is: lines( ellipse(x=covmat(Results,i,"row",1,2,FALSE), centre=Results@Rowprinccoord[i,cbind(1,2)], npoints=1000), cex=1, pch=".", col="blue") lines( ellipse(x=covmat(Results,i,"column",1,2,FALSE), centre=Results@Colprinccoord[i,cbind(1,2)], npoints=1000), cex=1, pch=".", col="blue") Note that `reflectaxes` will be needed if cabootcrs() and ca() axes are reflected with respect to each other ## Examples ```r results <- cabootcrs(DreamData, showresults=FALSE) row2covmataxes12 <- covmat(results,2,"row") col3covmataxes23 <- covmat(results,3,"column",2,3) ## Not run: # There are now 3 variables with 5,4,3 categories, hence 12 columns resultsmca <- cabootcrs(DreamData223by3, catype="mca", showresults=FALSE) row2covmataxes12mca <- covmat(resultsmca,2,"column") col3covmataxes23mca <- covmat(resultsmca,8,"column",2,3) newvarcat2covmataxes12mca <- covmat(resultsmca,11,"column") # Use ellipse() to put confidence regions around row points on a plot produced by ca(). # Note that reflectaxes() will be needed if cabootcrs() and ca() axes # are reflected with respect to each other library(ca) library(ellipse) TheData <- DreamData Results <- cabootcrs(TheData, showresults=FALSE) caResults <- ca(TheData) plot(caResults) for (i in 1:dim(TheData)[1]) { lines( ellipse(x=covmat(Results,i,"row",1,2,FALSE), centre=Results@Rowprinccoord[i,cbind(1,2)], npoints=1000), cex=1, pch=".", col="blue") } ## End(Not run) ``` ## See Also `cabootcrs-package`, `cabootcrs`, `allvarscovs`, `cabootcrsresults`

covmat function