PURPOSE: The objective of this presentation is to bring awareness to the challenges of missing data from study design and analysis perspectives, and to discuss study design elements and analysis methods that support meaningful and valid inferences in both prospective and retrospective observational research used to generate real-world evidence for payers and health technology assessment authorities. DESCRIPTION: Observational studies are increasingly used to study the post approval drug exposed population for drug and medical effectiveness and safety assessments. Understanding the potential sources of missing data from a study whose design imposes structure on data captured from real world clinical practice allows the selection of study design elements that may help reduce the magnitude of missing data. Given the occurrence of missing data, analysis methods that support valid and meaningful conclusions from observational research are necessary. This presentation starts with an overview of the potential sources of missing data in observational research, including PRO assessments and retrospective clinical data; then focuses on proactive planning of data collection and analysis. The types of missing data (missing due to study withdrawal; directly reported as missing; non-reported; uninterpretable value; out-of-range value) and statistical approaches for handling missing data including examining missing data patterns and testing missingness mechanisms, effective and advanced analytic methods (imputation, likelihood based and weighted approaches), when these methods should be applied, and the impact of missing data to the interpretation of study findings will be discussed. The concepts and methods will be explained with the use of real-world observational study data, including patient registries, electronic medical records, patient charts, and claims data.