alpha_estimation: alpha estimation procedure

In YipengUva/RpESCA: R implementaion of pESCA models with various concave penalties

Description

This function will estimate the noise level (alpha is the variation parameter) of a quantitative data set using the PCA model. The rank of the PCA model is selected using a missing value based cross validation procedure. The details of this function can be found in https://arxiv.org/abs/1902.06241.

Usage

alpha_estimation(X, K = 3, Rs = 1:15, opts = list())

Arguments

X	a quantitative data set
K	K-fold cross validation
Rs	the searching range of the number of components
opts	a list contains the setting for the algorithm. tol_obj: tolerance for relative change of hist_obj, default:1E-6; maxit: max number of iterations, default: 1000;

Value

This function returns a list contains

• alphas_mean: the mean of the K estimated alphas

• alphas_std: the std of the K estimated alphas

• R_CV: the number of PCs with minimum cross validation error

• cvErrors: K-fold cross validation errors

Examples

## Not run: alpha_estimation(X,K=3,Rs = 1:15,opts=list())

YipengUva/RpESCA documentation built on July 2, 2019, 6:41 p.m.