The function for nuisance parameter estimation in anchored_lasso_testing().
estimate_nuisance_parameter_lasso(
nuisance_sample_1,
nuisance_sample_2,
pca_method = "sparse_pca",
mean_method = "lasso",
lasso_tuning_method = "min",
num_latent_factor = 1,
local_environment = local_environment,
verbose = TRUE
)A list of estimated nuisance quantities.
Leading principle components
Sample mean for group 1
Sample mean for group 1
Logistic Lasso regression coefficients.
Anchored projection direction. It is similar to PC1 when signal is weak but similar to estimate_optimal_direction when the signal is moderately large.
Discriminant direction.
Group 1 sample. Each row is a subject and each column corresponds to a feature.
Group 2 sample. Each row is a subject and each column corresponds to a feature.
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.
Methods used to estimate the discriminant direction. Default is logistic Lasso "lasso". Can also take value "lasso_no_truncation"
Method for Lasso penalty hyperparameter tuning. Default is "min", the minimizer of cross-validation error; users can also use "1se" for more sparse solutions.
The principle component that lasso coefficient anchors at. The default is PC1 = 1.
An environment for hyperparameters shared between folds.
Print information to the console. Default is TRUE.