qut: automatic selection of nuclear norm regularization parameter

In genevievelrobin/lori: Imputation of High-Dimensional Count Data using Side Information

automatic selection of nuclear norm regularization parameter

Description

automatic selection of nuclear norm regularization parameter

Usage

qut(Y, cov, lambda2 = 0, q = 0.95, N = 100, reff = T, ceff = T)

Arguments

Y	A matrix of counts (contingency table).
cov	A (np)xK matrix of K covariates about rows and columns
lambda2	A positive number, the regularization parameter for covariates main effects
q	A number between 0 and 1. The quantile of the distribution of $lambda_QUT$ to take.
N	An integer. The number of parametric bootstrap samples to draw.
reff	[boolean] whether row effects should be fitted, default value is TRUE
ceff	[boolean] whether column effects should be fitted, default value is TRUE

Value

the value of $lambda_QUT$ to use in LoRI.

Examples

X = matrix(rnorm(30), 15)
Y = matrix(rpois(15, 1:15), 5)
lambda = qut(Y,X, 10, N=10)

genevievelrobin/lori documentation built on Nov. 21, 2024, 5:34 p.m.