Dataset Information

Reporting and dealing with missing quality of life data in RCTs: has the picture changed in the last decade?

ABSTRACT: PURPOSE:Missing data are a major problem in the analysis of data from randomised trials affecting power and potentially producing biased treatment effects. Specifically focussing on quality of life outcomes, we aimed to report the amount of missing data, whether imputation was used and what methods and was the missing mechanism discussed from four leading medical journals and compare the picture to our previous review nearly a decade ago. METHODS:A random selection (50 %) of all RCTS published during 2013-2014 in BMJ, JAMA, Lancet and NEJM was obtained. RCTs reported in research letters, cluster RCTs, non-randomised designs, review articles and meta-analysis were excluded. RESULTS:We included 87 RCTs in the review of which 35 % the amount of missing primary QoL data was unclear, 31 (36 %) used imputation. Only 23 % discussed the missing data mechanism. Nearly half used complete case analysis. Reporting was more unclear for secondary QoL outcomes. Compared to the previous review, multiple imputation was used more prominently but mainly in sensitivity analysis. CONCLUSIONS:Inadequate reporting and handling of missing QoL data in RCTs are still an issue. There is a large gap between statistical methods research relating to missing data and the use of the methods in applications. A sensitivity analysis should be undertaken to explore the sensitivity of the main results to different missing data assumptions. Medical journals can help to improve the situation by requiring higher standards of reporting and analytical methods to deal with missing data, and by issuing guidance to authors on expected standard.

SUBMITTER: Fielding S

PROVIDER: S-EPMC5102945 | biostudies-literature | 2016 Dec

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Reporting and dealing with missing quality of life data in RCTs: has the picture changed in the last decade?

Fielding S S Ogbuagu A A Sivasubramaniam S S MacLennan G G Ramsay C R CR

Quality of life research : an international journal of quality of life aspects of treatment, care and rehabilitation 20160920 12

<h4>Purpose</h4>Missing data are a major problem in the analysis of data from randomised trials affecting power and potentially producing biased treatment effects. Specifically focussing on quality of life outcomes, we aimed to report the amount of missing data, whether imputation was used and what methods and was the missing mechanism discussed from four leading medical journals and compare the picture to our previous review nearly a decade ago.<h4>Methods</h4>A random selection (50 %) of all R ...[more]

PMID: 27650288

Similar Datasets

Project description:BackgroundExtant literature suggests that a substantial portion of athletes may not report a possible concussion and that concussion knowledge is insufficient to predict concussion reporting behavior. One area that has not been explored is reporting skill; that is, mastery of the actions required to report a concussion. This study evaluated the relationship between reporting skill and reporting intention, introducing a measure of the reporting skill construct.HypothesesReporting intentions will be more closely associated with reporting skill than with concussion/symptom knowledge. The relationship between concussion (or symptom) knowledge and reporting intentions will differ by level of reporting skill.Study designRepeated cross-sectional study.Level of evidenceLevel 2.MethodsA set of items was administered to young adults aged 18 to 24 years from the Survey Sampling International panel. Exploratory/confirmatory factor analyses were conducted on 2 waves of data to develop the scale (n = 899). Hypotheses were tested using structural equation modeling on the responses from the third wave of participants (n = 406).ResultsKnowing the actions to take in reporting was more important than having knowledge of concussions or concussion symptoms. Reporting skill, not concussion or concussion symptom knowledge, was associated with higher intentions to report symptoms. Among those with higher levels of reporting skill, concussion symptom knowledge (but not general concussion knowledge) was associated with higher intentions to report symptoms.ConclusionReporting skill is an important and, until now, missing ingredient in the concussion literature and practice.Clinical relevanceIncorporating reporting skill development in concussion education and team activities to teach athletes how to report is likely to improve actual reporting intentions. While further study is needed with particular sports and additional age groups, reporting skill holds promise as a new avenue for increased concussion reporting.

Dataset Information

Reporting and dealing with missing quality of life data in RCTs: has the picture changed in the last decade?

Publications

Reporting and dealing with missing quality of life data in RCTs: has the picture changed in the last decade?

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets