Accounting for nonmonotone missing data using inverse probability weighting
Statistics in Medicine · 2023
DOI: 10.1002/sim.9860 ↗At a glance
Beobachtungsstudie in Statistics in Medicine, 2023. Written by Rachael K Ross and 5 co-authors. Institution: Department of Epidemiology, Gillings School of Global Public Health, University of North Carolina, Chapel Hill, North Carolina, USA. Major MEDLINE topics: Premature Birth. Cited 10 times so far (Crossref); 68 references. The full text is freely available in PubMed Central. Funded by: NIAID NIH HHS, NICHD NIH HHS, Eunice Kennedy Shriver National Institute of Child Health and Human Development.
Abstract (original language)
Inverse probability weighting can be used to correct for missing data. New estimators for the weights in the nonmonotone setting were introduced in 2018. These estimators are the unconstrained maximum likelihood estimator (UMLE) and the constrained Bayesian estimator (CBE), an alternative if UMLE fails to converge. In this work we describe and illustrate these estimators, and examine performance in simulation and in an applied example estimating the effect of anemia on spontaneous preterm birth in the Zambia Preterm Birth Prevention Study. We compare performance with multiple imputation (MI) and focus on the setting of an observational study where inverse probability of treatment weights are used to address confounding. In simulation, weighting was less statistically efficient at the smallest sample size and lowest exposure prevalence examined (n = 1500, 15% respectively) but in other scenarios statistical performance of weighting and MI was similar. Weighting had improved computational efficiency taking, on average, 0.4 and 0.05 times the time for MI in R and SAS, respectively. UMLE was easy to implement in commonly used software and convergence failure occurred just twice in >200 000 simulated cohorts making implementation of CBE unnecessary. In conclusion, weighting is an alternative to MI for nonmonotone missingness, though MI performed as well as or better in terms of bias and statistical efficiency. Weighting's superior computational efficiency may be preferred with large sample sizes or when using resampling algorithms. As validity of weighting and MI rely on correct specification of different models, both approaches could be implemented to check agreement of results.
Subjects
MeSH terms (MEDLINE)
Author keywords
Authors and institutions
- Department of Epidemiology, Gillings School of Global Public Health, University of North Carolina, Chapel Hill, North Carolina, USA.
- Department of Obstetrics and Gynecology, School of Medicine, University of North Carolina, Chapel Hill, North Carolina, USA.
ORCID profiles: Rachael K Ross, Jessie K Edwards
Funding
- NIAID NIH HHS
- NICHD NIH HHS
- Eunice Kennedy Shriver National Institute of Child Health and Human Development
- National Institute of Allergy and Infectious Diseases
Cite
APA
Ross, R. K., Cole, S. R., Edwards, J. K., Westreich, D., Daniels, J. L., & Stringer, J. S. A. (2023). Accounting for nonmonotone missing data using inverse probability weighting. Statistics in Medicine. https://doi.org/10.1002/sim.9860
Vancouver
Ross RK, Cole SR, Edwards JK, Westreich D, Daniels JL, Stringer JSA. Accounting for nonmonotone missing data using inverse probability weighting. Statistics in Medicine. 2023. doi:10.1002/sim.9860
BibTeX
@article{Ross2023,
author = {Ross, Rachael K and Cole, Stephen R and Edwards, Jessie K and Westreich, Daniel and Daniels, Julie L and Stringer, Jeffrey S A},
title = {Accounting for nonmonotone missing data using inverse probability weighting},
journal = {Statistics in Medicine},
year = {2023},
doi = {10.1002/sim.9860}
}
EUVIMED