When Listwise Deletion Works: Causal Diagrams and Complete-Case Regression
Abstract
Listwise deletion (LWD) appears more common than imputation: our review of leading journals finds that about 50% of articles state or imply LWD, versus 7% describing an imputation model. Assuming oracle regression with all required values observed consistently estimates the population average treatment effect, we ask when complete-case regression remains consistent. With constant effects, we offer two checks: whether covariates and the missing indicator satisfy the adjustment criterion in an augmented causal diagram (DAG), and whether the estimator pools valid within-covariate comparisons appropriately, potentially using inverse treatment-propensity weighting (IPW). For heterogeneous effects, assuming conditional effects carry over to the population, we reweight comparisons to the population covariate distribution. Simulations and empirical illustrations from American politics, comparative politics, and international relations demonstrate the framework's use and show why a missing-at-random (MAR) classification, although useful for assessing imputation, does not by itself establish whether complete-case regression consistently estimates the target population ATE. Thus, we recommend adding the missing indicator and its causes to causal models, then checking adjustment and weighting for LWD.
Related
- Finite deletion-induced saturation for every non-complete graph
- Deletion thresholds and exponential examples for complete sequences
- Anytime-Valid Inference in Linear Models with Applications to Regression-Adjusted Causal Inference
- Higher Order Asymptotics of Regression Adjustment Estimators for Causal Inference
- Residual-Based Causal Discovery via Pretrained In-Context Quantile Regression
BibTeX
@misc{lin2026when,
title = {{When Listwise Deletion Works: Causal Diagrams and Complete-Case Regression}},
author = {Wenxin Lin and Shiyao Liu},
howpublished = {arXiv},
year = {2026},
month = nov,
doi = {10.48550/arxiv.2611.04366},
eprint = {2611.04366},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2611.04366},
}
RIS
TY - UNPB
TI - When Listwise Deletion Works: Causal Diagrams and Complete-Case Regression
AU - Wenxin Lin
AU - Shiyao Liu
PY - 2026
DA - 2026/11/03
PB - arXiv
DO - 10.48550/arxiv.2611.04366
UR - https://arxiv.org/abs/2611.04366
AB - Listwise deletion (LWD) appears more common than imputation: our review of leading journals finds that about 50% of articles state or imply LWD, versus 7% describing an imputation model. Assuming oracle regression with all required values observed consistently estimates the population average treatment effect, we ask when complete-case regression remains consistent. With constant effects, we offer two checks: whether covariates and the missing indicator satisfy the adjustment criterion in an augmented causal diagram (DAG), and whether the estimator pools valid within-covariate comparisons appropriately, potentially using inverse treatment-propensity weighting (IPW). For heterogeneous effects, assuming conditional effects carry over to the population, we reweight comparisons to the population covariate distribution. Simulations and empirical illustrations from American politics, comparative politics, and international relations demonstrate the framework's use and show why a missing-at-random (MAR) classification, although useful for assessing imputation, does not by itself establish whether complete-case regression consistently estimates the target population ATE. Thus, we recommend adding the missing indicator and its causes to causal models, then checking adjustment and weighting for LWD.
ER -