Johanna Hardin

Ian Krupkin, Johanna Hardin

In this paper, error estimates of classification Random Forests are quantitatively assessed. Based on the initial theoretical framework built by Bates et al. (2023), the true error rate and expected error rate are theoretically and empirically investigated in the context of a variety of error estimation methods common to Random Forests. We show that in the classification case, Random Forests' estimates of prediction error is closer on average to the true error rate instead of the average prediction error. This is opposite the findings of Bates et al. (2023) which are given for logistic regression. We further show that our result holds across different error estimation strategies such as cross-validation, bagging, and data splitting.

Benjamin Lu, Johanna Hardin

We introduce a unified framework for random forest prediction error estimation based on a novel estimator of the conditional prediction error distribution function. Our framework enables simple plug-in estimation of key prediction uncertainty metrics, including conditional mean squared prediction errors, conditional biases, and conditional quantiles, for random forests and many variants. Our approach is especially well-adapted for prediction interval estimation; we show via simulations that our proposed prediction intervals are competitive with, and in some settings outperform, existing methods. To establish theoretical grounding for our framework, we prove pointwise uniform consistency of a more stringent version of our estimator of the conditional prediction error distribution function. The estimators introduced here are implemented in the R package forestError.