Open Access
December 2015 On the analysis of tuberculosis studies with intermittent missing sputum data
Daniel Scharfstein, Andrea Rotnitzky, Maria Abraham, Aidan McDermott, Richard Chaisson, Lawrence Geiter
Ann. Appl. Stat. 9(4): 2215-2236 (December 2015). DOI: 10.1214/15-AOAS860


In randomized studies evaluating treatments for tuberculosis (TB), individuals are scheduled to be routinely evaluated for the presence of TB using sputum cultures. One important endpoint in such studies is the time of culture conversion, the first visit at which a patient’s sputum culture is negative and remains negative. This article addresses how to draw inference about treatment effects when sputum cultures are intermittently missing on some patients. We discuss inference under a novel benchmark assumption and under a class of assumptions indexed by a treatment-specific sensitivity parameter that quantify departures from the benchmark assumption. We motivate and illustrate our approach using data from a randomized trial comparing the effectiveness of two treatments for adult TB patients in Brazil.


Download Citation

Daniel Scharfstein. Andrea Rotnitzky. Maria Abraham. Aidan McDermott. Richard Chaisson. Lawrence Geiter. "On the analysis of tuberculosis studies with intermittent missing sputum data." Ann. Appl. Stat. 9 (4) 2215 - 2236, December 2015.


Received: 1 May 2013; Revised: 1 July 2015; Published: December 2015
First available in Project Euclid: 28 January 2016

zbMATH: 06560828
MathSciNet: MR3456372
Digital Object Identifier: 10.1214/15-AOAS860

Keywords: Culture conversion , curse of dimensionality , exponential tilting , reverse-time hazard , sensitivity analysis

Rights: Copyright © 2015 Institute of Mathematical Statistics

Vol.9 • No. 4 • December 2015
Back to Top