h_many: Comparing CPC to set of eigenvectors

In bbolker/cpcbp: common principal components/back-projection analysis

Description

Tests whether to reject the null hypothesis that a set of q hypothetical eigenvectors are equal to the first q likelihood eigenvectors in CPC, based on equation 3.3 (Flury, 1986). The value q must be a value of 2 or greater. For q=1, see the function h_one.

Usage

  h_many(matList, n, betaList)

Arguments

matList	list of matrices
n	numeric vector of sample sizes
betaList	list of eigenvectors (organized from largest to smallest eigenvalue) to be compared to7

References

Flury B.N. Asymptotic theory for common principal component analysis. Annals Statist. 1986. 14, 418-430.

bbolker/cpcbp documentation built on May 11, 2019, 9:28 p.m.