fungible (version 2.2.2)

smoothKB: Smooth a Non PD Correlation Matrix using the Knol-Berger algorithm

Description

A function for smoothing a non-positive definite correlation matrix by the method of Knol and Berger (1991).

Usage

smoothKB(R, eps = 1e+08 * .Machine$double.eps)

Value

RKB

A Smoothed (positive definite) correlation matrix.

eps

Small positive number to control the size of the non-scaled smallest eigenvalue of the smoothed R matrix.

Arguments

R

A non-positive definite correlation matrix.

eps

Small positive number to control the size of the non-scaled smallest eigenvalue of the smoothed R matrix. Default = 1E8 * .Machine$double.eps

Author

Niels Waller

References

Knol, D. L., & Berger, M. P. F., (1991). Empirical comparison between factor analysis and multidimensional item response models.Multivariate Behavioral Research, 26, 457-477.

Examples

data(BadRLG)

## RKB = smoothed R
RKB<-smoothKB(R=BadRLG, eps = 1E8 * .Machine$double.eps)$RKB
print(eigen(RKB)$values)