Reporting and dealing with missing quality of life data in RCTs

has the picture changed in the last decade?

S. Fielding, A. Ogbuagu, S. Sivasubramaniam, G. MacLennan, C. R. Ramsay

Research output: Contribution to journalArticle

13 Citations (Scopus)
5 Downloads (Pure)

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.
Original languageEnglish
Pages (from-to)2977-2983
Number of pages7
JournalQuality of Life Research
Volume25
Issue number12
Early online date20 Sep 2016
DOIs
Publication statusPublished - Dec 2016

Fingerprint

Quality of Life
Research
Meta-Analysis

Keywords

  • missing data
  • quality of life
  • randomised controlled trial
  • imputation

Cite this

Reporting and dealing with missing quality of life data in RCTs : has the picture changed in the last decade? / Fielding, S.; Ogbuagu, A.; Sivasubramaniam, S.; MacLennan, G.; Ramsay, C. R.

In: Quality of Life Research, Vol. 25, No. 12, 12.2016, p. 2977-2983.

Research output: Contribution to journalArticle

@article{6c11cc86b03f4db4a8ee8d70b1db9db5,
title = "Reporting and dealing with missing quality of life data in RCTs: has the picture changed in the last decade?",
abstract = "PurposeMissing 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.MethodsA 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.ResultsWe 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.ConclusionsInadequate 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.",
keywords = "missing data, quality of life, randomised controlled trial, imputation",
author = "S. Fielding and A. Ogbuagu and S. Sivasubramaniam and G. MacLennan and Ramsay, {C. R.}",
year = "2016",
month = "12",
doi = "10.1007/s11136-016-1411-6",
language = "English",
volume = "25",
pages = "2977--2983",
journal = "Quality of Life Research",
issn = "0962-9343",
publisher = "Springer",
number = "12",

}

TY - JOUR

T1 - Reporting and dealing with missing quality of life data in RCTs

T2 - has the picture changed in the last decade?

AU - Fielding, S.

AU - Ogbuagu, A.

AU - Sivasubramaniam, S.

AU - MacLennan, G.

AU - Ramsay, C. R.

PY - 2016/12

Y1 - 2016/12

N2 - PurposeMissing 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.MethodsA 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.ResultsWe 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.ConclusionsInadequate 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.

AB - PurposeMissing 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.MethodsA 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.ResultsWe 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.ConclusionsInadequate 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.

KW - missing data

KW - quality of life

KW - randomised controlled trial

KW - imputation

U2 - 10.1007/s11136-016-1411-6

DO - 10.1007/s11136-016-1411-6

M3 - Article

VL - 25

SP - 2977

EP - 2983

JO - Quality of Life Research

JF - Quality of Life Research

SN - 0962-9343

IS - 12

ER -