Formal Hypothesis Tests for Additive Structure in Random Forests
This work addresses the need for statistical tools to investigate regression structure in ensemble learners like random forests, which is incremental as it builds on existing asymptotic properties.
The authors tackled the problem of interpretability and formal inference in random forests by developing formal hypothesis tests for variable importance and additive model structure, achieving these tests at no additional computational cost and proposing an efficient extension using random projections for high-dimensional settings.
While statistical learning methods have proved powerful tools for predictive modeling, the black-box nature of the models they produce can severely limit their interpretability and the ability to conduct formal inference. However, the natural structure of ensemble learners like bagged trees and random forests has been shown to admit desirable asymptotic properties when base learners are built with proper subsamples. In this work, we demonstrate that by defining an appropriate grid structure on the covariate space, we may carry out formal hypothesis tests for both variable importance and underlying additive model structure. To our knowledge, these tests represent the first statistical tools for investigating the underlying regression structure in a context such as random forests. We develop notions of total and partial additivity and further demonstrate that testing can be carried out at no additional computational cost by estimating the variance within the process of constructing the ensemble. Furthermore, we propose a novel extension of these testing procedures utilizing random projections in order to allow for computationally efficient testing procedures that retain high power even when the grid size is much larger than that of the training set.