Inference in randomized studies with informative censoring and discrete time-to-event endpoints

Daniel Scharfstein; James M. Robins; Wesley Eddings; Andrea Rotnitzky

doi:10.1111/j.0006-341X.2001.00404.x

Inference in randomized studies with informative censoring and discrete time-to-event endpoints

Daniel Scharfstein, James M. Robins, Wesley Eddings, Andrea Rotnitzky

Research output: Contribution to journal › Article › peer-review

36 Scopus citations

Abstract

In this article, we present a method for estimating and comparing the treatment-specific distributions of a discrete time-to-event variable from right-censored data. Our method allows for (1) adjustment for informative censoring due to measured prognostic factors for time to event and censoring and (2) quantification of the sensitivity of the inference to residual dependence between time to event and censoring due to unmeasured factors. We develop our approach in the context of a randomized trial for the treatment of chronic schizophrenia. We perform a simulation study to assess the practical performance of our methodology.

Original language	English (US)
Pages (from-to)	404-413
Number of pages	10
Journal	Biometrics
Volume	57
Issue number	2
DOIs	https://doi.org/10.1111/j.0006-341X.2001.00404.x
State	Published - Jun 2001
Externally published	Yes

Keywords

Coarsening at random
Competing risks
Curse of dimensionality
Inverse probability of censoring weighted estimation
Kaplan-Meier estimator
Sequential ignorability of censoring

ASJC Scopus subject areas

Statistics and Probability
Biochemistry, Genetics and Molecular Biology(all)
Immunology and Microbiology(all)
Agricultural and Biological Sciences(all)
Applied Mathematics

Access to Document

10.1111/j.0006-341X.2001.00404.x

Cite this

@article{a7c7ecb79a8f4b9f9ffbc15c000e34c9,

title = "Inference in randomized studies with informative censoring and discrete time-to-event endpoints",

abstract = "In this article, we present a method for estimating and comparing the treatment-specific distributions of a discrete time-to-event variable from right-censored data. Our method allows for (1) adjustment for informative censoring due to measured prognostic factors for time to event and censoring and (2) quantification of the sensitivity of the inference to residual dependence between time to event and censoring due to unmeasured factors. We develop our approach in the context of a randomized trial for the treatment of chronic schizophrenia. We perform a simulation study to assess the practical performance of our methodology.",

keywords = "Coarsening at random, Competing risks, Curse of dimensionality, Inverse probability of censoring weighted estimation, Kaplan-Meier estimator, Sequential ignorability of censoring",

author = "Daniel Scharfstein and Robins, {James M.} and Wesley Eddings and Andrea Rotnitzky",

year = "2001",

month = jun,

doi = "10.1111/j.0006-341X.2001.00404.x",

language = "English (US)",

volume = "57",

pages = "404--413",

journal = "Biometrics",

issn = "0006-341X",

publisher = "Wiley-Blackwell",

number = "2",

}

TY - JOUR

T1 - Inference in randomized studies with informative censoring and discrete time-to-event endpoints

AU - Scharfstein, Daniel

AU - Robins, James M.

AU - Eddings, Wesley

AU - Rotnitzky, Andrea

PY - 2001/6

Y1 - 2001/6

N2 - In this article, we present a method for estimating and comparing the treatment-specific distributions of a discrete time-to-event variable from right-censored data. Our method allows for (1) adjustment for informative censoring due to measured prognostic factors for time to event and censoring and (2) quantification of the sensitivity of the inference to residual dependence between time to event and censoring due to unmeasured factors. We develop our approach in the context of a randomized trial for the treatment of chronic schizophrenia. We perform a simulation study to assess the practical performance of our methodology.

AB - In this article, we present a method for estimating and comparing the treatment-specific distributions of a discrete time-to-event variable from right-censored data. Our method allows for (1) adjustment for informative censoring due to measured prognostic factors for time to event and censoring and (2) quantification of the sensitivity of the inference to residual dependence between time to event and censoring due to unmeasured factors. We develop our approach in the context of a randomized trial for the treatment of chronic schizophrenia. We perform a simulation study to assess the practical performance of our methodology.

KW - Coarsening at random

KW - Competing risks

KW - Curse of dimensionality

KW - Inverse probability of censoring weighted estimation

KW - Kaplan-Meier estimator

KW - Sequential ignorability of censoring

UR - http://www.scopus.com/inward/record.url?scp=0035000781&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0035000781&partnerID=8YFLogxK

U2 - 10.1111/j.0006-341X.2001.00404.x

DO - 10.1111/j.0006-341X.2001.00404.x

M3 - Article

C2 - 11414563

AN - SCOPUS:0035000781

SN - 0006-341X

VL - 57

SP - 404

EP - 413

JO - Biometrics

JF - Biometrics

IS - 2

ER -

Inference in randomized studies with informative censoring and discrete time-to-event endpoints

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this