Prediction Error Estimation in Random Forests
This provides a more accurate error estimation method for users of Random Forests in classification tasks, though it is incremental as it builds on existing theoretical frameworks.
The paper tackles the problem of estimating prediction error in classification Random Forests, showing that their error estimates are closer to the true error rate rather than the average prediction error, contrary to prior findings for logistic regression, and this result holds across methods like cross-validation and bagging.
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.