rapidsplithalf (version 0.6)

corByColumns: Correlate two matrices by column

Description

Correlate each column of 1 matrix with the same column in another matrix

Usage

corByColumns(x, y)
corByColumns_mask(x, y, mask)
corStatsByColumns(x, y)

Value

corByColumns() and corByColumns_mask() return a numeric vector of correlations of each pair of columns.

corStatsByColumns() returns a list with named items:

• cormean: the aggregated correlation coefficient of all column pairs (see Details)

• allcors: the correlations of each column pair

• xvar: the column variances of matrix x

• yvar: the column variances of matrix y

• covar: the covariances of each column pair

Arguments

x, y

Matrices whose values to correlate by column.

mask

Logical matrix marking which data points to include.

Author

Sercan Kahveci

Details

The primary use for these functions is to rapidly compute the correlations between two sets of split-half scores stored in matrix columns.

corStatsByColumns produces the mean correlation of all column-pairs using the formula mean(covariances) / sqrt(mean(col1variance) * mean(col2variance))

This method is more accurate than cormean() and was suggested by prof. John Christie of Dalhousie University.

Examples

m1<-matrix((1:9)+rnorm(9),ncol=3)
m2<-matrix((9:1)+rnorm(9),ncol=3)
corByColumns(m1,m2)

mask<-1-diag(3)
corByColumns_mask(m1,m2,mask)

corStatsByColumns(m1,m2)