What question did this study set out to answer?

To evaluate and compare the performance of statistical methods for addressing missing covariate data under a missing at random assumption in meta-regression models.

July 7, 2022Research Synthesis Methods

Comparing methods for handling missing covariates in meta‐regression

View Full Paper

Ask AI

Bookmark

To evaluate and compare the performance of statistical methods for addressing missing covariate data under a missing at random assumption in meta-regression models.
Conducted a simulation study comparing four missing data strategies: complete-case analysis (CCA), shifting-case analysis (SCA), multiple imputation (MI), and full information maximum likelihood (FIML).
Modeled missing covariate values under the assumption of a missing at random (MAR) mechanism.
Multiple imputation (MI) and full information maximum likelihood (FIML) outperformed ad hoc complete-case analysis (CCA) and shifting-case analysis (SCA).
Data deletion strategies yielded inferior estimation performance compared to model-based and imputation-based techniques in meta-regression.

Discussion

No takes yet. Share an insight, caveat, or question.

Implication

Simulation study demonstrates superior performance of multiple imputation and full information maximum likelihood over deletion methods, highlighting preferred approaches for missing covariates.

Cite This Study

Lee et al. (2022) studied this question.

synapsesocial.com/papers/6a725a48a528af2d65c46517 https://doi.org/10.1002/jrsm.1585

View Full Paper

Ask AI

Bookmark

Implication

Simulation study demonstrates superior performance of multiple imputation and full information maximum likelihood over deletion methods, highlighting preferred approaches for missing covariates.

Comparing methods for handling missing covariates in meta‐regression

Key Points

Discussion

Implication

Cite This Study

Comparing methods for handling missing covariates in meta‐regression

Key Points

Discussion

Implication

Cite This Study

Also Consider

Also Consider