Accounting for model uncertainty in multiple imputation under complex sampling

DOI10.1111/SJOS.12473MaRDI QIDQ5152174zbMATH OpenOpenAlexFDO

Authors Gyuhyeong Goh, Jae Kwang Kim

Publication date 17 September 2021

Published in Scandinavian Journal of Statistics (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1811.11950

zbMATH Keywords

approximate Bayesian computationBayesian model averagingmultiple imputationitem nonresponseinformative sampling

Mathematics Subject Classification ID

Bayesian inference (62F15) Sampling theory, sample surveys (62D05) Statistical ranking and selection procedures (62F07) Missing data (62D10)

Abstract: Multiple imputation provides an effective way to handle missing data. When several possible models are under consideration for the data, the multiple imputation is typically performed under a single-best model selected from the candidate models. This single model selection approach ignores the uncertainty associated with the model selection and so leads to underestimation of the variance of multiple imputation estimator. In this paper, we propose a new multiple imputation procedure incorporating model uncertainty in the final inference. The proposed method incorporates possible candidate models for the data into the imputation procedure using the idea of Bayesian Model Averaging (BMA). The proposed method is directly applicable to handling item nonresponse in survey sampling. Asymptotic properties of the proposed method are investigated. A limited simulation study confirms that our model averaging approach provides better estimation performance than the single model selection approach.

Recommendations

• A note on multiple imputation under complex sampling
• A multiple imputation approach to deal with the unity measure error
• Multiple imputation for the analysis of incomplete compound variables
• Nonparametric methods for the estimation of imputation uncertainty
• Addressing missing data mechanism uncertainty using multiple-model multiple imputation: application to a longitudinal clinical trial
• Multiple-model multiple imputation for longitudinal count data to address uncertainty in missingness mechanism
• Multiple imputation: current perspectives

Cited in

(6)

• A multiple imputation approach to deal with the unity measure error
• Model selection and model averaging after multiple imputation
• Multiple-model multiple imputation for longitudinal count data to address uncertainty in missingness mechanism
• Penalized estimating equations for generalized linear models with multiple imputation
• A two-step semiparametric method to accommodate sampling weights in multiple imputation
• A note on multiple imputation under complex sampling

This page was built for publication: Accounting for model uncertainty in multiple imputation under complex sampling

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5152174)