estimate_nuisance_pc {HMC}

The function for nuisance parameter estimation in simple_pc_testing() and debiased_pc_testing().

Description

The function for nuisance parameter estimation in simple_pc_testing() and debiased_pc_testing().

Usage

estimate_nuisance_pc(
  nuisance_sample_1,
  nuisance_sample_2 = NULL,
  pca_method = "sparse_pca",
  mean_method = "naive",
  num_latent_factor = 1,
  local_environment = NA
)

Arguments

nuisance_sample_1

Group 1 sample. Each row is a subject and each column corresponds to a feature.

nuisance_sample_2

Group 2 sample. Each row is a subject and each column corresponds to a feature.

pca_method

Methods used to estimate principle component The default is "sparse_pca", using sparse PCA from package PMA. Other choices are "dense_pca"—the regular PCA; and "hard"— hard-thresholding PCA, which also induces sparsity.

mean_method

Methods used to estimate the mean vector. Default is sample mean "naive". There is also a hard-thresholding sparse estiamtor "hard".

num_latent_factor

Number of principle to be estimated/tested. Default is 1.

local_environment

A environment for hyperparameters shared between folds.

Value

A list of estimated nuisance quantities.

estimate_leading_pc

Leading principle components

estimate_mean_1

Sample mean for group 1

estimate_mean_2

Sample mean for group 1

estimate_eigenvalue

Eigenvalue for each principle compoenent.

estimate_noise_variance

Noise variance, I need this to construct block-diagonal estimates of the covariance matrix.