evaluate_influence_function_multi_factor {HMC}

Calculate the test statistics on the left-out samples. Called in debiased_pc_testing().

Description

Calculate the test statistics on the left-out samples. Called in debiased_pc_testing().

Usage

evaluate_influence_function_multi_factor(
  cross_fitting_sample_1,
  cross_fitting_sample_2 = NULL,
  nuisance_collection,
  num_latent_factor = 1
)

Arguments

cross_fitting_sample_1

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

cross_fitting_sample_2

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

nuisance_collection

A collection of nuisance quantities estimated using "nuisance" samples. It is the output of estimate_nuisance_pc().

num_latent_factor

Number of principle components to be considered.

Value

A list of test statistics.

inner_product_1

Simple inner products for sample 1.

inner_product_2

Simple inner products for sample 2.

influence_eigenvector_each_subject_1

Debiased test statistics, sample 1.

influence_eigenvector_each_subject_2

Debiased test statistics, sample 1.

for_variance_subject_1

Statistics for variance calculation, sample 1.

for_variance_subject_2

Statistics for variance calculation, sample 2.