flury.AIC: AIC statistics for Flury's hierarchy

In tpepler/cpc: Common principal component (CPC) analysis and applications

AIC statistics for Flury's hierarchy

Description

Calculates the Akaike Information Criterion (AIC) for the higher model vs. the lower model in Flury's hierarchy of covariance matrices.

Usage

flury.AIC(covmats.high, covmats.low, nvec, df)

Arguments

covmats.high	Array of estimated covariance matrices under the higher model in Flury's hierarchy.
covmats.low	Array of estimated covariance matrices under the lower model in Flury's hierarchy.
nvec	Vector of sample sizes of the k groups.
df	Degrees of freedom of the higher model, versus the model of unrelated covariance matrices.

Details

This is a utility function used by flury.test, but can also be called directly if required.

Value

Returns the AIC value (scalar).

Author(s)

Theo Pepler

References

Flury, B. (1988). Common Principal Components and Related Multivariate Models. Wiley.

See Also

flury.test

tpepler/cpc documentation built on July 7, 2022, 2:13 a.m.