On logistic regression with right censored data, with or without competing risks, and its use for estimating treatment effects

Research output: Contribution to journal › Journal article › Research › peer-review

Standard

On logistic regression with right censored data, with or without competing risks, and its use for estimating treatment effects. / Blanche, Paul Frederic; Holt, Anders; Scheike, Thomas.

In: Lifetime Data Analysis, Vol. 29, 2023, p. 441–482.

Research output: Contribution to journal › Journal article › Research › peer-review

Harvard

Blanche, PF, Holt, A & Scheike, T 2023, 'On logistic regression with right censored data, with or without competing risks, and its use for estimating treatment effects', Lifetime Data Analysis, vol. 29, pp. 441–482. https://doi.org/10.1007/s10985-022-09564-6

APA

Blanche, P. F., Holt, A., & Scheike, T. (2023). On logistic regression with right censored data, with or without competing risks, and its use for estimating treatment effects. Lifetime Data Analysis, 29, 441–482. https://doi.org/10.1007/s10985-022-09564-6

Vancouver

Blanche PF, Holt A, Scheike T. On logistic regression with right censored data, with or without competing risks, and its use for estimating treatment effects. Lifetime Data Analysis. 2023;29:441–482. https://doi.org/10.1007/s10985-022-09564-6

Author

Blanche, Paul Frederic ; Holt, Anders ; Scheike, Thomas. / On logistic regression with right censored data, with or without competing risks, and its use for estimating treatment effects. In: Lifetime Data Analysis. 2023 ; Vol. 29. pp. 441–482.

Bibtex

@article{28c1f344a13146288f3d35082cc3edca,
title = "On logistic regression with right censored data, with or without competing risks, and its use for estimating treatment effects",
abstract = "Simple logistic regression can be adapted to deal with right-censoring by inverse probability of censoring weighting (IPCW). We here compare two such IPCW approaches, one based on weighting the outcome, the other based on weighting the estimating equations. We study the large sample properties of the two approaches and show that which of the two weighting methods is the most efficient depends on the censoring distribution. We show by theoretical computations that the methods can be surprisingly different in realistic settings. We further show how to use the two weighting approaches for logistic regression to estimate causal treatment effects, for both observational studies and randomized clinical trials (RCT). Several estimators for observational studies are compared and we present an application to registry data. We also revisit interesting robustness properties of logistic regression in the context of RCTs, with a particular focus on the IPCW weighting. We find that these robustness properties still hold when the censoring weights are correctly specified, but not necessarily otherwise.",
keywords = "Average treatment effect, Competing risks, Ipcw adjustment, Logistic regression, COVARIATE ADJUSTMENT, CAUSAL INFERENCE, MODELS, TRIALS, EFFICIENCY, FAILURE, TESTS",
author = "Blanche, {Paul Frederic} and Anders Holt and Thomas Scheike",
year = "2023",
doi = "10.1007/s10985-022-09564-6",
language = "English",
volume = "29",
pages = "441–482",
journal = "Lifetime Data Analysis",
issn = "1380-7870",
publisher = "Springer",

}

RIS

TY - JOUR

T1 - On logistic regression with right censored data, with or without competing risks, and its use for estimating treatment effects

AU - Blanche, Paul Frederic

AU - Holt, Anders

AU - Scheike, Thomas

PY - 2023

Y1 - 2023

N2 - Simple logistic regression can be adapted to deal with right-censoring by inverse probability of censoring weighting (IPCW). We here compare two such IPCW approaches, one based on weighting the outcome, the other based on weighting the estimating equations. We study the large sample properties of the two approaches and show that which of the two weighting methods is the most efficient depends on the censoring distribution. We show by theoretical computations that the methods can be surprisingly different in realistic settings. We further show how to use the two weighting approaches for logistic regression to estimate causal treatment effects, for both observational studies and randomized clinical trials (RCT). Several estimators for observational studies are compared and we present an application to registry data. We also revisit interesting robustness properties of logistic regression in the context of RCTs, with a particular focus on the IPCW weighting. We find that these robustness properties still hold when the censoring weights are correctly specified, but not necessarily otherwise.

AB - Simple logistic regression can be adapted to deal with right-censoring by inverse probability of censoring weighting (IPCW). We here compare two such IPCW approaches, one based on weighting the outcome, the other based on weighting the estimating equations. We study the large sample properties of the two approaches and show that which of the two weighting methods is the most efficient depends on the censoring distribution. We show by theoretical computations that the methods can be surprisingly different in realistic settings. We further show how to use the two weighting approaches for logistic regression to estimate causal treatment effects, for both observational studies and randomized clinical trials (RCT). Several estimators for observational studies are compared and we present an application to registry data. We also revisit interesting robustness properties of logistic regression in the context of RCTs, with a particular focus on the IPCW weighting. We find that these robustness properties still hold when the censoring weights are correctly specified, but not necessarily otherwise.

KW - Average treatment effect

KW - Competing risks

KW - Ipcw adjustment

KW - Logistic regression

KW - COVARIATE ADJUSTMENT

KW - CAUSAL INFERENCE

KW - MODELS

KW - TRIALS

KW - EFFICIENCY

KW - FAILURE

KW - TESTS

U2 - 10.1007/s10985-022-09564-6

DO - 10.1007/s10985-022-09564-6

M3 - Journal article

C2 - 35799026

VL - 29

SP - 441

EP - 482

JO - Lifetime Data Analysis

JF - Lifetime Data Analysis

SN - 1380-7870

ER -

ID: 313862253