Reserved factor-analytic and G-matrix extractors — factor_g

Usage

genetic_loadings(object, ...)

specific_variance(object, ...)

latent_breeding_values(object, ...)

Arguments

object: A fitted model object.
...: Reserved for future arguments.

Value

specific_variance() returns named Psi for the bounded FA fit; the other factor extractors error for hsquared_fit objects.

Details

The bounded four-trait rank-one factor-analytic opt-in reports G, genetic correlations, and specific_variance() (Psi). Loading columns (genetic_loadings()) and latent breeding values (latent_breeding_values()) are rotation-nonunique until a rotation or constraint policy is validated. Future hsquared_fit methods reserve effect and rotation controls, but these controls currently error rather than implying that loading axes are interpretable. The rotation-invariant genetic eigenstructure and evolvability geometry are available now via eigen_G() and the g_matrix_geometry family.

For G = Lambda Lambda' + diag(Psi), rotating Lambda leaves Psi unchanged. The four-trait rank-one FA parameterization is locally identifiable up to a sign change only with a regular, sufficiently nonzero loading pattern. Sparse or weak loadings and boundary fits can leave Psi poorly identified. specific_variance() returns the named Psi vector for this opt-in fit and errors for other fits.