CVEK: Robust Estimation and Testing for Nonlinear Effects using Kernel Machine Ensemble

TL;DR

CVEK is an R package that employs ensemble kernel machine learning to robustly estimate and test nonlinear effects and interactions among covariates in limited sample settings.

Contribution

The paper introduces CVEK, a flexible R package implementing ensemble kernel methods for nonlinear effect estimation and hypothesis testing, with extensive validation and practical guidelines.

Findings

CVEK provides valid and robust nonlinear effect estimates.

The package supports diverse kernels and ensembling methods.

Simulation results demonstrate its effectiveness across scenarios.

Abstract

The R package CVEK introduces a suite of flexible machine learning models and robust hypothesis tests for learning the joint nonlinear effects of multiple covariates in limited samples. It implements the Cross-validated Ensemble of Kernels (CVEK)(Liu and Coull 2017), an ensemble-based kernel machine learning method that adaptively learns the joint nonlinear effect of multiple covariates from data, and provides powerful hypothesis tests for both main effects of features and interactions among features. The R Package CVEK provides a flexible, easy-to-use implementation of CVEK, and offers a wide range of choices for the kernel family (for instance, polynomial, radial basis functions, Mat\'ern, neural network, and others), model selection criteria, ensembling method (averaging, exponential weighting, cross-validated stacking), and the type of hypothesis test (asymptotic or parametric bootstrap). Through extensive simulations we demonstrate the validity and robustness of this approach, and provide practical guidelines on how to design an estimation strategy for optimal performance in different data scenarios.