# Fast Causal Inference with Non-Random Missingness by Test-Wise Deletion

arXiv: https://arxiv.org/abs/1705.09031 · HTML: https://mlsanity.com/paper/1705.09031/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 May 2017.

## Built on by (most cited first, 23 of 23)

- [Deep End-to-end Causal Inference](https://mlsanity.com/paper/2202.02195/) (2022)
- [A survey of Bayesian Network structure learning](https://mlsanity.com/paper/2109.11415/) (2021)
- [A Survey on Causal Discovery: Theory and Practice](https://mlsanity.com/paper/2305.10032/) (2023)
- [Discovering Causal Relations and Equations from Data](https://mlsanity.com/paper/2305.13341/) (2023)
- [CUTS: Neural Causal Discovery from Irregular Time-Series Data](https://mlsanity.com/paper/2302.07458/) (2023)
- [Causal Structure Learning Supervised by Large Language Model](https://mlsanity.com/paper/2311.11689/) (2023)
- [Simultaneous Missing Value Imputation and Structure Learning with Groups](https://mlsanity.com/paper/2110.08223/) (2021)
- [Greedy structure learning from data that contain systematic missing values](https://mlsanity.com/paper/2107.04184/) (2021)
- [Gene Regulatory Network Inference in the Presence of Dropouts: a Causal View](https://mlsanity.com/paper/2403.15500/) (2024)
- [Why Do Probabilistic Clinical Models Fail To Transport Between Sites?](https://mlsanity.com/paper/2311.04787/) (2023)
- [Optimal Transport for Structure Learning Under Missing Data](https://mlsanity.com/paper/2402.15255/) (2024)
- [Identification of Causal Structure in the Presence of Missing Data with Additive Noise Model](https://mlsanity.com/paper/2312.12206/) (2023)
- [Causal Inference with Latent Variables: Recent Advances and Future Prospectives](https://mlsanity.com/paper/2406.13966/) (2024)
- [Entropic Inequality Constraints from e-separation Relations in Directed Acyclic Graphs with Hidden Variables](https://mlsanity.com/paper/2107.07087/) (2021)
- [Multiple imputation and test-wise deletion for causal discovery with incomplete cohort data](https://mlsanity.com/paper/2108.13331/) (2021)
- [Risk Assessment of Lymph Node Metastases in Endometrial Cancer Patients: A Causal Approach](https://mlsanity.com/paper/2305.10041/) (2023)
- [GLACIAL: Granger and Learning-based Causality Analysis for Longitudinal Imaging Studies](https://mlsanity.com/paper/2210.07416/) (2022)
- [Learning Cyclic Causal Models from Incomplete Data](https://mlsanity.com/paper/2402.15625/) (2024)
- [MissNODAG: Differentiable Cyclic Causal Graph Learning from Incomplete Data](https://mlsanity.com/paper/2410.18918/) (2024)
- [Accelerating Causal Network Discovery of Alzheimer Disease Biomarkers via Scientific Literature-based Retrieval Augmented Generation](https://mlsanity.com/paper/2504.08768/) (2025)
- [Robust Causal Discovery in Real-World Time Series with Power-Laws](https://mlsanity.com/paper/2507.12257/) (2025)
- [Causal Discovery for Cross-Sectional Data Based on Super-Structure and Divide-and-Conquer](https://mlsanity.com/paper/2602.03914/) (2026)
- [Generalizing Identifiability Results in Causal Discovery from Complete Data to Missing Data Settings](https://mlsanity.com/paper/2610.19211/) (2026)

## Abstract (arXiv)

Many real datasets contain values missing not at random (MNAR). In this scenario, investigators often perform list-wise deletion, or delete samples with any missing values, before applying causal discovery algorithms. List-wise deletion is a sound and general strategy when paired with algorithms such as FCI and RFCI, but the deletion procedure also eliminates otherwise good samples that contain only a few missing values. In this report, we show that we can more efficiently utilize the observed values with test-wise deletion while still maintaining algorithmic soundness. Here, test-wise deletion refers to the process of list-wise deleting samples only among the variables required for each conditional independence (CI) test used in constraint-based searches. Test-wise deletion therefore often saves more samples than list-wise deletion for each CI test, especially when we have a sparse underlying graph. Our theoretical results show that test-wise deletion is sound under the justifiable assumption that none of the missingness mechanisms causally affect each other in the underlying causal graph. We also find that FCI and RFCI with test-wise deletion outperform their list-wise deletion and imputation counterparts on average when MNAR holds in both synthetic and real data.