A general method for handling missing binary outcome data in randomized controlled trials.
rct · Level II
Where this comes from
- Record sourced from PubMed, PMID 25171441.
- Also identified by DOI 10.1111/add.12721 and PMC identifier 4241048.
- Licence recorded as CC BY.
- The licence permits redistribution, so the abstract is shown in full and the full text is available from the publisher.
Abstract
The analysis of randomized controlled trials with incomplete binary outcome data is challenging. We develop a general method for exploring the impact of missing data in such trials, with a focus on abstinence outcomes. We propose a sensitivity analysis where standard analyses, which could include 'missing = smoking' and 'last observation carried forward', are embedded in a wider class of models. We apply our general method to data from two smoking cessation trials. A total of 489 and 1758 participants from two smoking cessation trials. The abstinence outcomes were obtained using telephone interviews. The estimated intervention effects from both trials depend on the sensitivity parameters used. The findings differ considerably in magnitude and statistical significance under quite extreme assumptions about the missing data, but are reasonably consistent under more moderate assumptions. A new method for undertaking sensitivity analyses when handling missing data in trials with binary outcomes allows a wide range of assumptions about the missing data to be assessed. In two smoking cessation trials the results were insensitive to all but extreme assumptions.
Medical subject headings
- Data Collection
- Data Collection/methods
- Data Collection/statistics & numerical data
- Humans
- Models, Statistical
- Outcome Assessment, Health Care
- Outcome Assessment, Health Care/statistics & numerical data
- Randomized Controlled Trials as Topic
- Randomized Controlled Trials as Topic/statistics & numerical data
- Research Design
- Smoking Cessation
- Smoking Cessation/methods
- Smoking Cessation/statistics & numerical data