cor2meanAdj: adjusted average square correlation by rows

In ldstatsHD: Linear Dependence Statistics for High-Dimensional Data

Description

Finds in a computationally fast algorithm the adjusted average square correlation magnitude for every variable of a dataset.

Usage

cor2mean.adj(mat)

Arguments

mat	p \times n matrix with the p-variate dataset.

Details

The adjusted average square correlation of variable i is given by

(n-1)/(n-2) \bar{r}_{i}^2 - 1/(n-2)

where n is the sample size and \bar{r}_{i}^2 is the average square correlation matrix for the ith row, which is computed by cor2mean.

Value

A vector containing the adjusted square average correlation (excluding diagonal) for every variable.

Author(s)

Mayer, Claus, Adria Caballe and Natalia Bochkina.

References

To come

See Also

cor2mean for average square correlations.

Examples

EX1        <- pcorSimulator(nobs = 50, nclusters= 3, nnodesxcluster = c(100,30,50), 
                            pattern = "powerLaw", plus = 0)
corsEX1     <- cor2mean(t(EX1$y))
corsadjEX1  <- cor2mean.adj(t(EX1$y))

ldstatsHD documentation built on Aug. 14, 2017, 5:06 p.m.