Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2017 Jun;73(2):431-440.
doi: 10.1111/biom.12594. Epub 2016 Oct 17.

Inference in randomized trials with death and missingness

Chenguang Wang  1 , Daniel O Scharfstein  2 , Elizabeth Colantuoni  2 , Timothy D Girard  3 , Ying Yan  4
Affiliations

Inference in randomized trials with death and missingness

Chenguang Wang et al. Biometrics. 2017 Jun.

Abstract

In randomized studies involving severely ill patients, functional outcomes are often unobserved due to missed clinic visits, premature withdrawal, or death. It is well known that if these unobserved functional outcomes are not handled properly, biased treatment comparisons can be produced. In this article, we propose a procedure for comparing treatments that is based on a composite endpoint that combines information on both the functional outcome and survival. We further propose a missing data imputation scheme and sensitivity analysis strategy to handle the unobserved functional outcomes not due to death. Illustrations of the proposed method are given by analyzing data from a recent non-small cell lung cancer clinical trial and a recent trial of sedation interruption among mechanically ventilated patients.

Keywords: Composite endpoint; Death-truncated data; Missing data; Sensitivity analysis.

PubMed Disclaimer

Figures

Figure 1:
Figure 1:
Cumulative distribution function of the composite endpoint for each treatment group based on the multiple imputation algorithm with the benchmark assumptions. The composite endpoint is labeled according to the survival time L among patients that die and the functional endpoint Z among patients that survive to 12 weeks.
Figure 2:
Figure 2:
Treatment-specific densities of the imputed Z (average change in LBM from baseline) for different choices of the sensitivity parameters βT
Figure 3:
Figure 3:
Sensitivity analysis: Panel (A) presents estimates of θ (with 95% confidence intervals) for various choices of the sensitivity analysis parameters. Note that β1 and β0 are the sensitivity analysis parameters for the anamorelin and Placebo groups, respectively. Panel (B) presents the treatment-specific estimates of the median (with 95% confidence intervals) of the composite endpoint for various choices of sensitivity analysis parameters. Panel (C) presents the contour plot of the p-values obtained by testing the null hypothesis of θ = 0 as function of treatment-specific sensitivity analysis parameters.
See this image and copyright information in PMC

References

    1. Birmingham J, Rotnitzky A, and Fitzmaurice GM (2003). Pattern-mixture and selection models for analysing longitudinal data with monotone missing patterns. Journal of the Royal Statistical Society: Series B 65, 275–297.
    1. Chiba Y and VanderWeele TJ (2011). A simple method for principal strata effects when the outcome has been truncated due to death. American Journal of Epidemiology 173, 745–751. - PMC - PubMed
    1. Cowles MK and Carlin BP (1996). Markov Chain Monte Carlo convergence diagnostics: a comparative review. Journal of the American Statistical Association 91, 883–904.
    1. Daniels M and Hogan J (2008). Missing Data in Longitudinal Studies: Strategies for Bayesian Modeling and Sensitivity Analysis. CRC Press.
    1. Diehr P, Patrick DL, Spertus J, Kiefe CI, Donell M, and Fihn SD (2001). Transforming self-rated health and the SF-36 scales to include death to improve interpretability. Medical Care 39, 670–680. - PubMed