Package index • msaenet

Data simulation

Generate simulation data.

msaenet.sim.gaussian(): Generate Simulation Data for Benchmarking Sparse Regressions (Gaussian Response)

msaenet.sim.binomial(): Generate Simulation Data for Benchmarking Sparse Regressions (Binomial Response)

msaenet.sim.poisson(): Generate Simulation Data for Benchmarking Sparse Regressions (Poisson Response)

msaenet.sim.cox(): Generate Simulation Data for Benchmarking Sparse Regressions (Cox Model)

Model fitting

Fit adaptive and multi-step estimation models based on elastic-net, MCP-net, or SCAD-net penalties.

aenet(): Adaptive Elastic-Net

msaenet(): Multi-Step Adaptive Elastic-Net

amnet(): Adaptive MCP-Net

msamnet(): Multi-Step Adaptive MCP-Net

asnet(): Adaptive SCAD-Net

msasnet(): Multi-Step Adaptive SCAD-Net

msaenet-package: msaenet: Multi-Step Adaptive Estimation Methods for Sparse Regressions

Inference and plotting

Visualize the fitted model and predict on new data.

plot(<msaenet>): Plot msaenet Model Objects

predict(<msaenet>): Make Predictions from an msaenet Model

print(<msaenet>): Print msaenet Model Information

Model inspection

Inspect the fitted models with more details.

msaenet.nzv(): Get Indices of Non-Zero Variables

msaenet.nzv.all(): Get Indices of Non-Zero Variables in All Steps

msaenet.tp(): Get the Number of True Positive Selections

msaenet.fp(): Get the Number of False Positive Selections

msaenet.fn(): Get the Number of False Negative Selections

coef(<msaenet>): Extract Model Coefficients

Model evaluation

Compute performance evaluation metrics.

msaenet.rmse(): Root Mean Squared Error (RMSE)

msaenet.mse(): Mean Squared Error (MSE)

msaenet.mae(): Mean Absolute Error (MAE)

msaenet.rmsle(): Root Mean Squared Logarithmic Error (RMSLE)