# Imputation Uncertainty in Interpretable Machine Learning Methods

arXiv: https://arxiv.org/abs/2512.17689 · HTML: https://mlsanity.com/paper/2512.17689/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 35 references that are in the map.
- First posted on arXiv 19 Dec 2025.

## Builds on (most cited first, 11 of 11)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [All Models are Wrong, but Many are Useful: Learning a Variable's Importance by Studying an Entire Class of Prediction Models Simultaneously](https://mlsanity.com/paper/1801.01489/) (2018)
- [European Union regulations on algorithmic decision-making and a "right to explanation"](https://mlsanity.com/paper/1606.08813/) (2016)
- [Reliable Post hoc Explanations: Modeling Uncertainty in Explainability](https://mlsanity.com/paper/2008.05030/) (2020)
- [Efficient nonparametric statistical inference on population feature importance using Shapley values](https://mlsanity.com/paper/2006.09481/) (2020)
- [Relating the Partial Dependence Plot and Permutation Feature Importance to the Data Generating Process](https://mlsanity.com/paper/2109.01433/) (2021)
- [Classification of datasets with imputed missing values: does imputation quality matter?](https://mlsanity.com/paper/2206.08478/) (2022)
- [Explainability of Machine Learning Models under Missing Data](https://mlsanity.com/paper/2407.00411/) (2024)
- [From interpretability to inference: an estimation framework for universal approximators](https://mlsanity.com/paper/1903.04209/) (2019)
- [Bootstrap Inference when Using Multiple Imputation](https://mlsanity.com/paper/1602.07933/) (2016)

## Abstract (arXiv)

In real data, missing values occur frequently, which affects the interpretation with interpretable machine learning (IML) methods. Recent work considers bias and shows that model explanations may differ between imputation methods, while ignoring additional imputation uncertainty and its influence on variance and confidence intervals. We therefore compare the effects of different imputation methods on the confidence interval coverage probabilities of the IML methods permutation feature importance, partial dependence plots and Shapley values. We show that single imputation leads to underestimation of variance and that, in most cases, only multiple imputation is close to nominal coverage.