Missing Data Imputation with Baseline Information in Longitudinal Clinical Trials

• Activity Number: 299 - Estimands and Imputations Methods
• Type: Contributed
• Date/Time: Tuesday, July 30, 2019 : 8:30 AM to 10:20 AM
• Sponsor: Biopharmaceutical Section
• Author(s): Yilong Zhang* and Zachary Zimmer and Lei Xu and Gregory Golm and Raymond Lam and Susan Huyck and Frank G Liu
• Companies: Merck and Merck and Merck and Merck and Merck and Merck and Merck Sharp & Dohme Inc.
• Keywords: clinical trials; longitudinal data; missing data; baseline observation carried forward; return to baseline; multiple imputation

Abstract

In longitudinal clinical trials, missing data is inevitable despite every effort made to retain patients in the trial. Missing data causes difficulty in the estimation and interpretation of the treatment effect. When the primary objective is to assess the treatment effect in a realistic setting, it is necessary to take into consideration the impact of noncompliance to the treatment regimen. For estimation following the intention-to-treat (ITT) principle, the US Food and Drug Administration (FDA) has recently required that sponsors use an return-to-baseline (RTB) approach for continuous endpoints in some longitudinal clinical trials. The RTB approach is based on the assumption that the unobserved outcomes at the end of the trial represent a return to the baseline value, i.e., any improvement or worsening of the clinical condition observed while on treatment can be expected to wash out once the patients drop out. RTB is similar to baseline-observation-carried-forward (BOCF), except that RTB adds random error to the imputed values. This paper investigates the statistical properties of this RTB approach. The method for calculating the sample size using RTB approach is also presented.