R: Applying re-parameterization from log-determinant of penalty...

Sl.repara {mgcv}

R Documentation

Applying re-parameterization from log-determinant of penalty matrix to model matrix.

INTERNAL routine to apply re-parameterization from log-determinant of penalty matrix, ldetS to model matrix, X, blockwise.

Sl.repara(rp, X, inverse = FALSE, both.sides = TRUE)

`rp`	reparametrization.
`X`	if `X` is a matrix it is assumed to be a model matrix whereas if `X` is a vector it is assumed to be a parameter vector.
`inverse`	if `TRUE` an inverse re-parametrization is performed.
`both.sides`	if `inverse==TRUE` and `both.sides==FALSE` then the re-parametrization only applied to rhs, as appropriate for a choleski factor. If `both.sides==FALSE`, `X` is a vector and `inverse==FALSE` then `X` is taken as a coefficient vector (so re-parametrization is inverse of that for the model matrix).

A re-parametrized version of X.

Simon N. Wood <simon.wood@r-project.org>.

[Package mgcv version 1.8-23 Index]