svdLSplus {WALS} | R Documentation |
Internal function: Uses SVD components to compute final estimate via Sherman-Morrison-Woodbury formula.
Description
Solves the equation system in walsNB via Sherman-Morrison-Woodbury formula
for the unrestricted estimator .
Usage
svdLSplus(U, V, singularVals, y, ell, geB)
Arguments
U |
Left singular vectors of |
V |
Right singular vectors of |
singularVals |
Singular values of |
y |
"Pseudo"-response, see details. |
ell |
Vector |
geB |
Scalar |
Details
The function can be reused for the computation of the fully restricted
estimator and the model averaged estimator
.
For and
use
U
, V
and singularVals
from SVD of .
For and
use same
pseudo-response
in argument
y
.
For use pseudo-response
.
See section "Note on function svdLSplus from WALS" in Huynh (2024b).
References
Huynh K (2024b). “WALS: Weighted-Average Least Squares Model Averaging in R.” University of Basel. Mimeo.