Resurrecting complete-case analysis: a defense
American Journal of Epidemiology · 2026
DOI: 10.1093/aje/kwaf284 ↗Kurz gefasst
Fachartikel in der Zeitschrift American Journal of Epidemiology, 2026. Verfasst von Maya B Mathur und 2 weiteren Autor:innen. Beteiligte Einrichtung: Quantitative Sciences Unit and Department of Pediatrics, School of Medicine, Stanford University, Palo Alto, CA, United States. Hauptthemen laut MEDLINE: Data Interpretation, Statistical. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 51 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NIH HHS, National Institutes of Health.
Abstract (Originalsprache)
Complete-case analysis (CCA) is often criticized because of the belief that CCA is only valid if data are missing completely at random. Influential papers therefore recommend abandoning CCA in favor of methods that make the weaker missing-at-random (MAR) assumption. We argue for a different view: CCA with principled covariate adjustment usefully complements MAR-based methods, such as multiple imputation (MI). When estimating treatment effects, appropriate covariate control can, for some causal structures, eliminate bias in CCA. This can be true even when data are missing not at random and when MAR-based methods are biased. We describe principles for choosing adjustment covariates for CCA, and we characterize the causal structures for which covariate adjustment does, or does not, eliminate bias. Even when CCA is biased, principled covariate adjustment often reduces the bias of CCA, and this method will sometimes be less biased than MI and other MAR-based methods. Therefore, when MI is used under the MAR assumption, adjusted CCA remains an important sensitivity analysis. When conducted with the same attention to covariate control that epidemiologists already afford to confounding, adjusted CCA belongs in the suite of reasonable methods for missing data. There is thus good justification for resurrecting CCA as a principled method.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Quantitative Sciences Unit and Department of Pediatrics, School of Medicine, Stanford University, Palo Alto, CA, United States.
- Department of Computer Science, Johns Hopkins University, Baltimore, MD, United States.
- Department of Epidemiology, Harvard University, Boston, MA, United States.
ORCID-Profile: Maya B Mathur, Ilya Shpitser, Tyler J VanderWeele
Förderung
- NIH HHS
- National Institutes of Health
Zitieren
APA
Mathur, M. B., Shpitser, I., & VanderWeele, T. J. (2026). Resurrecting complete-case analysis: a defense. American Journal of Epidemiology. https://doi.org/10.1093/aje/kwaf284
Vancouver
Mathur MB, Shpitser I, VanderWeele TJ. Resurrecting complete-case analysis: a defense. American Journal of Epidemiology. 2026. doi:10.1093/aje/kwaf284
BibTeX
@article{Mathur2026,
author = {Mathur, Maya B and Shpitser, Ilya and VanderWeele, Tyler J},
title = {Resurrecting complete-case analysis: a defense},
journal = {American Journal of Epidemiology},
year = {2026},
doi = {10.1093/aje/kwaf284}
}
EUVIMED