undoShrinkage: Undo shrinkage.

In ZhengguoGu/RegularizedSCA: Regularized Simultaneous Component Based Data Integration

Description

undoShrinkage re-estimates the component loading matrix (P) while keeping the 0 loadings fixed so as to remove the shrinkage due to Lasso and Group Lasso.

Usage

undoShrinkage(DATA, R, Phat, MAXITER)

Arguments

DATA	The concatenated data block, with rows representing subjects
R	The number of components.
Phat	The estimated component loading matrix by means of, for example, sparseSCA().
MAXITER	The maximum rounds of iterations. It should be a positive integer. The default value is 400.

Value

Pmatrix	The re-estimated component loading matrix after the shrinkage has been removed.
Tmatrix	The corresponding estimated component score matrix.
Lossvec	A vector of loss.

References

Gu, Z., & Van Deun, K. (2016). A variable selection method for simultaneous component based data integration. Chemometrics and Intelligent Laboratory Systems, 158, 187-199.

ZhengguoGu/RegularizedSCA documentation built on July 4, 2019, 2:46 p.m.