greedy: Factor Loading Adaptive Shrinkage (K factors version using...

In kkdey/flashr: Factor Loading Adaptive SHrinkage in R

Description

flash provide rank K matrix decomposition with greedy algorithm

Usage

greedy(Y, K, flash_para = list(), plugin = FALSE, gvalue = c("lik",
  "eigen"))

Arguments

Y	is the data matrix (N by P)
K	is the max number of factor user want. the output will provide the actual number of factor automaticaly.
flash_para	is the list for input parameters for flash
gvalue	is the output style of greedy algorithm, "lik" provide the lowerbound of loglikelihood "eigen" provide the sudo eigenvalue for each factor.

Details

greedy algorithm on the residual matrix to get a rank one matrix decomposition

Value

list of factor, loading and variance of noise matrix

• l is a N by K matrix for loadings

• f is a P by K matrix for factors

Examples

N = 100
P = 200
Y = matrix(rnorm(N*P,0,1),ncol=P)
g = greedy(Y,10)

kkdey/flashr documentation built on May 20, 2019, 10:36 a.m.