Skip to contents

Get significant principal components

Usage

get_sig_pcs(x, pc_method = c("mp", "gd"), verbose = FALSE)

Arguments

x

A data frame or matrix of methylation values; rows = features, columns = samples

pc_method

String indicating the method for estimating dimension; "gd" = Gavish-Donoho (default), "mp" = Marchenko-Pastur

verbose

Boolean; print output statements

Value

List containing four elements; sig_pcs = significant PCs, percent_var = percent variance explained, loadings = PC loadings, est_dim = estimated dimension

Examples

x <- diag(4)
get_sig_pcs(x, "gd")
#> $sig_pcs
#>             PC1
#> 1  6.952263e-17
#> 2  7.715167e-01
#> 3 -1.543033e-01
#> 4 -6.172134e-01
#> 
#> $percent_var
#>                                  PC1
#> percent_variance_explained 0.3333333
#> 
#> $loadings
#>             PC1
#> 1  5.192593e-17
#> 2  7.715167e-01
#> 3 -1.543033e-01
#> 4 -6.172134e-01
#> 
#> $est_dim
#> [1] 1
#>