Rank-based principal stratum sensitivity analyses

Stat Med. 2013 Nov 20;32(26):4526-39. doi: 10.1002/sim.5849. Epub 2013 May 19.

Abstract

We describe rank-based approaches to assess principal stratification treatment effects in studies where the outcome of interest is only well-defined in a subgroup selected after randomization. Our methods are sensitivity analyses, in that estimands are identified by fixing a parameter and then we investigate the sensitivity of results by varying this parameter over a range of plausible values. We present three rank-based test statistics and compare their performance through simulations, and provide recommendations. We also study three different bootstrap approaches for determining levels of significance. Finally, we apply our methods to two studies: an HIV vaccine trial and a prostate cancer prevention trial.

Keywords: causal inference; monotonicity; non-normality; principal stratification; ranks.

MeSH terms

  • AIDS Vaccines / standards
  • Computer Simulation
  • Data Interpretation, Statistical*
  • Finasteride / therapeutic use
  • HIV Infections / prevention & control
  • Humans
  • Male
  • Prostatic Neoplasms / drug therapy
  • Treatment Outcome*

Substances

  • AIDS Vaccines
  • Finasteride