Identification and Estimation of Causal Estimands with Missing Not at Random Data
Abstract
Missing not at random (MNAR) data pose significant challenges for causal inference, particularly when both confounders and the outcome are partially observed. Without additional assumptions beyond those required for causal inference, causal estimands are generally not identifiable under MNAR mechanisms. This paper first develops identification results for the causal estimand, the average treatment effect, under several plausible MNAR mechanisms using completeness conditions, and proposes an estimation approach based on the Expectation-Maximization (EM) algorithm. We further extend this identification and estimation framework to mediation analysis, enabling the estimation of natural direct and indirect effects under MNAR mechanisms. Through extensive simulation studies, we compare the proposed method with two widely used approaches for handling missing data, complete-case analysis and multiple imputation. The results show that the proposed method yields substantially lower bias under the considered MNAR mechanisms. Finally, we apply the proposed approach to NHANES data to estimate the causal effect of education on depression, with health condition as the mediator.
Related
- Causal Mediation Analysis with High-Dimensional Surrogates: Identification, Estimation and Inference under Latent Factor Models
- Estimands and estimation in trials with time trends
- Not Just Why, but When and for Whom: Revisiting Common Estimands in Causal Inference
- Generalizing Identifiability Results in Causal Discovery from Complete Data to Missing Data Settings
- The Missing Corner: When Sharp Causal Bounds Fail to Compose
BibTeX
@misc{ria2026identification,
title = {{Identification and Estimation of Causal Estimands with Missing Not at Random Data}},
author = {Faria Rauf Ria and Tarikul Islam and Mahbub A. H. M. Latif},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.20113},
eprint = {2609.20113},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.20113},
note = {CC BY-NC-ND 4.0},
}
RIS
TY - UNPB
TI - Identification and Estimation of Causal Estimands with Missing Not at Random Data
AU - Faria Rauf Ria
AU - Tarikul Islam
AU - Mahbub A. H. M. Latif
PY - 2026
DA - 2026/09/17
PB - arXiv
DO - 10.48550/arxiv.2609.20113
UR - https://arxiv.org/abs/2609.20113
AB - Missing not at random (MNAR) data pose significant challenges for causal inference, particularly when both confounders and the outcome are partially observed. Without additional assumptions beyond those required for causal inference, causal estimands are generally not identifiable under MNAR mechanisms. This paper first develops identification results for the causal estimand, the average treatment effect, under several plausible MNAR mechanisms using completeness conditions, and proposes an estimation approach based on the Expectation-Maximization (EM) algorithm. We further extend this identification and estimation framework to mediation analysis, enabling the estimation of natural direct and indirect effects under MNAR mechanisms. Through extensive simulation studies, we compare the proposed method with two widely used approaches for handling missing data, complete-case analysis and multiple imputation. The results show that the proposed method yields substantially lower bias under the considered MNAR mechanisms. Finally, we apply the proposed approach to NHANES data to estimate the causal effect of education on depression, with health condition as the mediator.
ER -