RRR: Reduced-rank regression with a given rank

In xliu-stat/NRRR: Multivariate Functional Regression via Nested Reduced-Rank Regularization

Description

This function provides the reduced-rank regression estimator with a given rank.

Usage

RRR(Y, X, nrank = 1, weight = FALSE, Gamma = diag(ncol(Y)),
    ypy.svd = TRUE, c.svd = FALSE)

Arguments

Y	response matrix.
X	design matrix.
nrank	a user-specified rank. Default is 1.
weight	a logical value. If TRUE, then the weighted criterion is employed. Default is FALSE.
Gamma	a weight matrix. Default is an identity matrix.
ypy.svd	a logical value. If TRUE (default), then the singular value decomposition method is used. If FALSE, then the eigenvalue decomposition method is used.
c.svd	a logical value. If TRUE, then output the singular value decomposition of the estimated coefficient matrix. Default is FALSE.

Value

The function returns a list:

C	the reduced-rank estimator.
C_ls	the least square estimator.
rank	the rank value.

References

Velu, R., & Reinsel, G. C. (2013). Multivariate reduced-rank regression: theory and applications (Vol. 136). Springer Science & Business Media.

xliu-stat/NRRR documentation built on Jan. 9, 2021, 3:23 p.m.