Abstract Administrative health data provide valuable insights into healthcare, but missing data remains a major barrier to ensuring the veracity of findings. This paper presents a structured approach to addressing missingness in administrative datasets, focusing on data assessment and statistical methods. Using causal diagrams and understanding the types of missing data to guide appropriate analytical strategies aligned with the Treatment And Reporting of Missing data in Observational Studies (TARMOS) framework. A real-world example demonstrates multiple imputations in large-scale health research. By promoting transparent and rigorous methods, this methods paper enhances the reliability and policy relevance of administrative data-based healthcare research.
Lin et al. (Fri,) studied this question.