1. 1376Modern concepts in the handling and reporting of missing data.
- Author
-
Lee, Katherine, Carpenter, James, Little, Roderick, Nguyen, Cattram, and Cornish, Rosie
- Subjects
- *
MULTIPLE imputation (Statistics) , *MISSING data (Statistics) , *DECISION making , *DATA distribution , *REPRODUCIBLE research , *SENSITIVITY analysis - Abstract
Focus and outcomes for participants Missing data are ubiquitous in observational studies, and the simple solution of restricting the analyses to the subset with complete records will often result in bias and loss of power. The seriousness of these issues for resulting inferences depends on both the mechanism causing the missing data and the form of the substantive question and associated model. The methodological literature on methods for the analysis of partially observed data has grown substantially over the last twenty years, and although there is increasing guidance on how to handle missing data, practice is changing slowly and misapprehensions abound, particularly in observational research. Importantly, the lack of transparency around methodological decisions regarding the analysis is threatening the validity and reproducibility of modern research. In this symposium leading researchers in missing data methodology will present practical guidance on how to select an appropriate method to handle missing data, describe how to report the results from such an analysis and describe how to conduct sensitivity analyses in the multiple imputation framework. Rationale for the symposium, including for its inclusion in the Congress One of the sub-themes of WCE 2021 is "Translation from research to policy and practice". Although there is a growing body of literature surrounding missing data methodology, evidence from systematic reviews suggests that missing data is still often not handled appropriately. If practice is to change, it is important to educate applied researchers regarding the available methodology and provide practical guidance on how to determine the best method for handling missing data. An important part of this is providing guidance on the reporting of results from analyses with missing data. This is particularly pertinent given the current emphasis on reproducibility of research findings. In this symposium we bring some of the latest research from the Missing Data Topic Group of the STRengthening Analytical Thinking for Observational Studies (STRATOS) initiative whose aim is to provide accessible and accurate guidance in the design and analysis of observational studies in order to increasie the reliability and validity of observational research. Presentation program Causal Diagrams to guide the treatment of missing data in epidemiological studies – With incomplete data, the "missing at random" (MAR) assumption is widely understood to enable unbiased estimation with appropriate methods. However, MAR is difficult to define in the context of multivariate missingness. In this talk, causal diagrams are introduced as an alternative framework for specifying practically accessible assumptions regarding missing data. The concept of recoverability is also introduced, which reflects whether a given parameter can be expressed as functions of the available data distribution and thus estimated consistently using the data alone. This concept can be used to guide the choice of method for handling missing data, and in particular whether sensitivity analyses allowing for data to be missing not at random are necessary. A comparison of three popular methods for handling missing data: complete case analysis, weighting and multiple imputation – In this talk the three most common methods for handling missing data are compared and contrasted. In particular, the strengths and weakness of each approach is discussed, and guidelines are provided regarding when each of the methods might be adopted over the others. The methods are illustrated on data from the Youth Cohort Study (YCS) of England, Wales and Scotland, 1984-2002. Sensitivity analyses using the Not at Random Fully Conditional Specification (NARFCS) procedure – Standard implementations of multiple imputation are only warranted to yield unbiased estimates under the missing at random (MAR) assumption, but its plausibility can only be assessed using subject-matter knowledge, not data. Therefore, it is important to perform sensitivity analyses to explore the robustness of results to assumptions concerning the missingness mechanism. In this talk we present the NARFCS procedure for conducting multivariate imputation under missing not at random (MNAR) assumptions. Using a case study from the Longitudinal Study of Australian Children, we illustrate a sensitivity analysis using the NARFCS procedure. We work through the steps involved, from deciding to perform the sensitivity analysis, and specifying the sensitivity parameters, through to carrying out the sensitivity analysis using NARFCS, which is implemented using multiple imputation by chained equation procedures in R and Stata. Framework for the treatment and reporting of missing data in observational studies: The Treatment And Reporting of Missing data in Observational Studies (TARMOS) framework – This talk outlines a practical framework for handling and reporting the analysis of incomplete data in observational studies, illustrated using a case study from the Avon Longitudinal Study of Parents and Children. The framework consists of three steps: 1) Develop an analysis plan specifying the analysis model and how missing data are going to be addressed. An important consideration is whether a complete records' analysis is likely to be valid, whether multiple imputation or an alternative approach is likely to offer benefits and whether a sensitivity analysis regarding the missingness mechanism is required; 2) Examine the data, checking the methods outlined in the analysis plan are appropriate, and conduct the preplanned analysis; and 3) Report the results, including a description of the missing data, details on how the missing data were addressed, and the results from all analyses, interpreted in light of the missing data and the clinical relevance. This framework seeks to support researchers in thinking systematically about missing data and transparently reporting the potential effect on the study results, therefore increasing the confidence in and reproducibility of research findings. Names of presenters Katherine Lee Roderick Little Cattram Nguyen Rosie Cornish [ABSTRACT FROM AUTHOR]
- Published
- 2021
- Full Text
- View/download PDF