Missing data handling in non-inferiority and equivalence trials

A systematic review

Brooke A. Rabe, Simon Day, Mallorie H. Fiero, Melanie L Bell

Research output: Contribution to journalArticle

Abstract

Background: Non-inferiority (NI) and equivalence clinical trials test whether a new treatment is therapeutically no worse than, or equivalent to, an existing standard of care. Missing data in clinical trials have been shown to reduce statistical power and potentially bias estimates of effect size; however, in NI and equivalence trials, they present additional issues. For instance, they may decrease sensitivity to differences between treatment groups and bias toward the alternative hypothesis of NI (or equivalence). Aims: Our primary aim was to review the extent of and methods for handling missing data (model-based methods, single imputation, multiple imputation, complete case), the analysis sets used (Intention-To-Treat, Per-Protocol, or both), and whether sensitivity analyses were used to explore departures from assumptions about the missing data. Methods: We conducted a systematic review of NI and equivalence trials published between May 2015 and April 2016 by searching the PubMed database. Articles were reviewed primarily by 2 reviewers, with 6 articles reviewed by both reviewers to establish consensus. Results: Of 109 selected articles, 93% reported some missing data in the primary outcome. Among those, 50% reported complete case analysis, and 28% reported single imputation approaches for handling missing data. Only 32% reported conducting analyses of both intention-to-treat and per-protocol populations. Only 11% conducted any sensitivity analyses to test assumptions with respect to missing data. Conclusion: Missing data are common in NI and equivalence trials, and they are often handled by methods which may bias estimates and lead to incorrect conclusions.

Original languageEnglish (US)
JournalPharmaceutical Statistics
DOIs
StateAccepted/In press - Jan 1 2018

Fingerprint

Non-inferiority
Data Handling
Missing Data
Equivalence
Clinical Trials
Imputation
Intention to Treat Analysis
Standard of Care
PubMed
Consensus
Databases
Statistical Power
Multiple Imputation
Effect Size
Review
Handling (Psychology)
Estimate
Data Model
Population
Model-based

ASJC Scopus subject areas

  • Statistics and Probability
  • Pharmacology
  • Pharmacology (medical)

Cite this

Missing data handling in non-inferiority and equivalence trials : A systematic review. / Rabe, Brooke A.; Day, Simon; Fiero, Mallorie H.; Bell, Melanie L.

In: Pharmaceutical Statistics, 01.01.2018.

Research output: Contribution to journalArticle

@article{cfab9f86a2cd404f91e081f66dc4cbec,
title = "Missing data handling in non-inferiority and equivalence trials: A systematic review",
abstract = "Background: Non-inferiority (NI) and equivalence clinical trials test whether a new treatment is therapeutically no worse than, or equivalent to, an existing standard of care. Missing data in clinical trials have been shown to reduce statistical power and potentially bias estimates of effect size; however, in NI and equivalence trials, they present additional issues. For instance, they may decrease sensitivity to differences between treatment groups and bias toward the alternative hypothesis of NI (or equivalence). Aims: Our primary aim was to review the extent of and methods for handling missing data (model-based methods, single imputation, multiple imputation, complete case), the analysis sets used (Intention-To-Treat, Per-Protocol, or both), and whether sensitivity analyses were used to explore departures from assumptions about the missing data. Methods: We conducted a systematic review of NI and equivalence trials published between May 2015 and April 2016 by searching the PubMed database. Articles were reviewed primarily by 2 reviewers, with 6 articles reviewed by both reviewers to establish consensus. Results: Of 109 selected articles, 93{\%} reported some missing data in the primary outcome. Among those, 50{\%} reported complete case analysis, and 28{\%} reported single imputation approaches for handling missing data. Only 32{\%} reported conducting analyses of both intention-to-treat and per-protocol populations. Only 11{\%} conducted any sensitivity analyses to test assumptions with respect to missing data. Conclusion: Missing data are common in NI and equivalence trials, and they are often handled by methods which may bias estimates and lead to incorrect conclusions.",
author = "Rabe, {Brooke A.} and Simon Day and Fiero, {Mallorie H.} and Bell, {Melanie L}",
year = "2018",
month = "1",
day = "1",
doi = "10.1002/pst.1867",
language = "English (US)",
journal = "Pharmaceutical Statistics",
issn = "1539-1604",
publisher = "John Wiley and Sons Ltd",

}

TY - JOUR

T1 - Missing data handling in non-inferiority and equivalence trials

T2 - A systematic review

AU - Rabe, Brooke A.

AU - Day, Simon

AU - Fiero, Mallorie H.

AU - Bell, Melanie L

PY - 2018/1/1

Y1 - 2018/1/1

N2 - Background: Non-inferiority (NI) and equivalence clinical trials test whether a new treatment is therapeutically no worse than, or equivalent to, an existing standard of care. Missing data in clinical trials have been shown to reduce statistical power and potentially bias estimates of effect size; however, in NI and equivalence trials, they present additional issues. For instance, they may decrease sensitivity to differences between treatment groups and bias toward the alternative hypothesis of NI (or equivalence). Aims: Our primary aim was to review the extent of and methods for handling missing data (model-based methods, single imputation, multiple imputation, complete case), the analysis sets used (Intention-To-Treat, Per-Protocol, or both), and whether sensitivity analyses were used to explore departures from assumptions about the missing data. Methods: We conducted a systematic review of NI and equivalence trials published between May 2015 and April 2016 by searching the PubMed database. Articles were reviewed primarily by 2 reviewers, with 6 articles reviewed by both reviewers to establish consensus. Results: Of 109 selected articles, 93% reported some missing data in the primary outcome. Among those, 50% reported complete case analysis, and 28% reported single imputation approaches for handling missing data. Only 32% reported conducting analyses of both intention-to-treat and per-protocol populations. Only 11% conducted any sensitivity analyses to test assumptions with respect to missing data. Conclusion: Missing data are common in NI and equivalence trials, and they are often handled by methods which may bias estimates and lead to incorrect conclusions.

AB - Background: Non-inferiority (NI) and equivalence clinical trials test whether a new treatment is therapeutically no worse than, or equivalent to, an existing standard of care. Missing data in clinical trials have been shown to reduce statistical power and potentially bias estimates of effect size; however, in NI and equivalence trials, they present additional issues. For instance, they may decrease sensitivity to differences between treatment groups and bias toward the alternative hypothesis of NI (or equivalence). Aims: Our primary aim was to review the extent of and methods for handling missing data (model-based methods, single imputation, multiple imputation, complete case), the analysis sets used (Intention-To-Treat, Per-Protocol, or both), and whether sensitivity analyses were used to explore departures from assumptions about the missing data. Methods: We conducted a systematic review of NI and equivalence trials published between May 2015 and April 2016 by searching the PubMed database. Articles were reviewed primarily by 2 reviewers, with 6 articles reviewed by both reviewers to establish consensus. Results: Of 109 selected articles, 93% reported some missing data in the primary outcome. Among those, 50% reported complete case analysis, and 28% reported single imputation approaches for handling missing data. Only 32% reported conducting analyses of both intention-to-treat and per-protocol populations. Only 11% conducted any sensitivity analyses to test assumptions with respect to missing data. Conclusion: Missing data are common in NI and equivalence trials, and they are often handled by methods which may bias estimates and lead to incorrect conclusions.

UR - http://www.scopus.com/inward/record.url?scp=85047465074&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85047465074&partnerID=8YFLogxK

U2 - 10.1002/pst.1867

DO - 10.1002/pst.1867

M3 - Article

JO - Pharmaceutical Statistics

JF - Pharmaceutical Statistics

SN - 1539-1604

ER -