Display options
Share it on

J R Stat Soc Series B Stat Methodol. 2015 Mar 01;77(2):397-415. doi: 10.1111/rssb.12072.

Semiparametric transformation models for causal inference in time to event studies with all-or-nothing compliance.

Journal of the Royal Statistical Society. Series B, Statistical methodology

Wen Yu, Kani Chen, Michael E Sobel, Zhiliang Ying

Affiliations

  1. Fudan University, Shanghai, China.
  2. Hong Kong University of Science and Technology, Hong Kong.
  3. Columbia University, New York, USA.

PMID: 25870521 PMCID: PMC4392345 DOI: 10.1111/rssb.12072

Abstract

We consider causal inference in randomized survival studies with right censored outcomes and all-or-nothing compliance, using semiparametric transformation models to estimate the distribution of survival times in treatment and control groups, conditional on covariates and latent compliance type. Estimands depending on these distributions, for example, the complier average causal effect (CACE), the complier effect on survival beyond time

Keywords: All-or-nothing compliance; Complier average causal effect; Instrumental variable; Randomized trials; Semiparametric transformation models; Survival analysis

References

  1. Biometrics. 2012 Dec;68(4):1037-45 - PubMed
  2. Stat Med. 2006 Jun 30;25(12):1981-2007 - PubMed
  3. Stat Med. 1994 Nov 15;13(21):2269-78 - PubMed
  4. Stat Med. 1993 Sep 15;12(17):1605-28 - PubMed
  5. Biometrics. 2009 Mar;65(1):96-103 - PubMed
  6. Biometrics. 2011 Dec;67(4):1397-405 - PubMed
  7. Stat Med. 2001 Aug 15;20(15):2287-304 - PubMed
  8. Stat Med. 1991 Jan;10(1):45-52 - PubMed
  9. Biostatistics. 2000 Mar;1(1):69-88 - PubMed
  10. Stat Med. 1997 May 15;16(9):1017-29 - PubMed
  11. Biometrics. 2011 Mar;67(1):319-23; discussion 323-5 - PubMed
  12. Biometrics. 2003 Mar;59(1):100-5 - PubMed

Publication Types

Grant support