Global sensitivity analysis of clinical trials with missing patient-reported outcomes

Research output: Contribution to journalArticle

Abstract

Randomized trials with patient-reported outcomes are commonly plagued by missing data. The analysis of such trials relies on untestable assumptions about the missing data mechanism. To address this issue, it has been recommended that the sensitivity of the trial results to assumptions should be a mandatory reporting requirement. In this paper, we discuss a recently developed methodology (Scharfstein et al., Biometrics, 2018) for conducting sensitivity analysis of randomized trials in which outcomes are scheduled to be measured at fixed points in time after randomization and some subjects prematurely withdraw from study participation. The methodology is explicated in the context of a placebo-controlled randomized trial designed to evaluate a treatment for bipolar disorder. We present a comprehensive data analysis and a simulation study to evaluate the performance of the method. A software package entitled SAMON (R and SAS versions) that implements our methods is available at www.missingdatamatters.org.

Original languageEnglish (US)
JournalStatistical Methods in Medical Research
DOIs
StateAccepted/In press - Jan 1 2018

Fingerprint

Randomized Trial
Global Analysis
Clinical Trials
Sensitivity Analysis
Mandatory Reporting
Missing Data Mechanism
Randomized Controlled Trial
Methodology
Evaluate
Random Allocation
Randomisation
Missing Data
Bipolar Disorder
Software Package
Biometrics
Disorder
Data analysis
Software
Randomized Controlled Trials
Fixed point

Keywords

  • Corrected estimator
  • exponential tilting
  • identifiability
  • missing not at random
  • plug-in estimator
  • smoothing

ASJC Scopus subject areas

  • Epidemiology
  • Statistics and Probability
  • Health Information Management

Cite this

@article{c01ed7c6c16442d0bbe115f8580cf659,
title = "Global sensitivity analysis of clinical trials with missing patient-reported outcomes",
abstract = "Randomized trials with patient-reported outcomes are commonly plagued by missing data. The analysis of such trials relies on untestable assumptions about the missing data mechanism. To address this issue, it has been recommended that the sensitivity of the trial results to assumptions should be a mandatory reporting requirement. In this paper, we discuss a recently developed methodology (Scharfstein et al., Biometrics, 2018) for conducting sensitivity analysis of randomized trials in which outcomes are scheduled to be measured at fixed points in time after randomization and some subjects prematurely withdraw from study participation. The methodology is explicated in the context of a placebo-controlled randomized trial designed to evaluate a treatment for bipolar disorder. We present a comprehensive data analysis and a simulation study to evaluate the performance of the method. A software package entitled SAMON (R and SAS versions) that implements our methods is available at www.missingdatamatters.org.",
keywords = "Corrected estimator, exponential tilting, identifiability, missing not at random, plug-in estimator, smoothing",
author = "Scharfstein, {Daniel O} and Aidan McDermott",
year = "2018",
month = "1",
day = "1",
doi = "10.1177/0962280218759565",
language = "English (US)",
journal = "Statistical Methods in Medical Research",
issn = "0962-2802",
publisher = "SAGE Publications Ltd",

}

TY - JOUR

T1 - Global sensitivity analysis of clinical trials with missing patient-reported outcomes

AU - Scharfstein, Daniel O

AU - McDermott, Aidan

PY - 2018/1/1

Y1 - 2018/1/1

N2 - Randomized trials with patient-reported outcomes are commonly plagued by missing data. The analysis of such trials relies on untestable assumptions about the missing data mechanism. To address this issue, it has been recommended that the sensitivity of the trial results to assumptions should be a mandatory reporting requirement. In this paper, we discuss a recently developed methodology (Scharfstein et al., Biometrics, 2018) for conducting sensitivity analysis of randomized trials in which outcomes are scheduled to be measured at fixed points in time after randomization and some subjects prematurely withdraw from study participation. The methodology is explicated in the context of a placebo-controlled randomized trial designed to evaluate a treatment for bipolar disorder. We present a comprehensive data analysis and a simulation study to evaluate the performance of the method. A software package entitled SAMON (R and SAS versions) that implements our methods is available at www.missingdatamatters.org.

AB - Randomized trials with patient-reported outcomes are commonly plagued by missing data. The analysis of such trials relies on untestable assumptions about the missing data mechanism. To address this issue, it has been recommended that the sensitivity of the trial results to assumptions should be a mandatory reporting requirement. In this paper, we discuss a recently developed methodology (Scharfstein et al., Biometrics, 2018) for conducting sensitivity analysis of randomized trials in which outcomes are scheduled to be measured at fixed points in time after randomization and some subjects prematurely withdraw from study participation. The methodology is explicated in the context of a placebo-controlled randomized trial designed to evaluate a treatment for bipolar disorder. We present a comprehensive data analysis and a simulation study to evaluate the performance of the method. A software package entitled SAMON (R and SAS versions) that implements our methods is available at www.missingdatamatters.org.

KW - Corrected estimator

KW - exponential tilting

KW - identifiability

KW - missing not at random

KW - plug-in estimator

KW - smoothing

UR - http://www.scopus.com/inward/record.url?scp=85044345804&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85044345804&partnerID=8YFLogxK

U2 - 10.1177/0962280218759565

DO - 10.1177/0962280218759565

M3 - Article

JO - Statistical Methods in Medical Research

JF - Statistical Methods in Medical Research

SN - 0962-2802

ER -