Development of guidelines to reduce, handle and report missing data in palliative care trials: A multi-stakeholder modified nominal group technique.

Abstract

Missing data can introduce bias and reduce the power, precision and generalisability of study findings. Guidelines on how to address missing data are limited in scope and detail, and poorly implemented. To develop guidelines on how best to (i) reduce, (ii) handle and (iii) report missing data in palliative care clinical trials. Modified nominal group technique. Patient and public research partners, palliative care clinicians, trialists, methodologists and statisticians attended a 1-day workshop, following which a multi-stakeholder development group drafted the guidelines. Seven main recommendations for reducing missing data, nine for handling missing data and twelve for reporting missing data were developed. The top five recommendations were: (i) train all research staff on missing data, (ii) prepare for missing data at the trial design stage, (iii) address missing data in the statistical analysis plan, (iv) collect the reasons for missing data and (v) report descriptive statistics comparing the baseline characteristics of those with missing and observed data. Reducing missing data, preparing for missing data and understanding the reasons for missing data were greater priorities for stakeholders than how to deal with missing data once they had occurred. Comprehensive guidelines on how to address missing data were developed by stakeholders involved in palliative care trials. Implementation of the guidelines will require endorsement of research funders and research journals.