Causality and the Cox Regression Model

Department of Public Health

Causality and the Cox Regression Model

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

Standard

Causality and the Cox Regression Model. / Martinussen, Torben.

In: Annual Review of Statistics and Its Application, Vol. 9, 2022, p. 249-259.

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

Harvard

Martinussen, T 2022, 'Causality and the Cox Regression Model', Annual Review of Statistics and Its Application, vol. 9, pp. 249-259. https://doi.org/10.1146/annurev-statistics-040320-114441

APA

Martinussen, T. (2022). Causality and the Cox Regression Model. Annual Review of Statistics and Its Application, 9, 249-259. https://doi.org/10.1146/annurev-statistics-040320-114441

Vancouver

Martinussen T. Causality and the Cox Regression Model. Annual Review of Statistics and Its Application. 2022;9:249-259. https://doi.org/10.1146/annurev-statistics-040320-114441

Author

Martinussen, Torben. / Causality and the Cox Regression Model. In: Annual Review of Statistics and Its Application. 2022 ; Vol. 9. pp. 249-259.

Bibtex

@article{ffef3c8e187a471fa272e7facb701d0d,

title = "Causality and the Cox Regression Model",

abstract = "This article surveys results concerning the interpretation of the Cox hazard ratio in connection to causality in a randomized study with a time-To-event response. The Cox model is assumed to be correctly specified, and we investigate whether the typical end product of such an analysis, the estimated hazard ratio, has a causal interpretation as a hazard ratio. It has been pointed out that this is not possible due to selection. We provide more insight into the interpretation of hazard ratios and differences, investigating what can be learned about a treatment effect from the hazard ratio approaching unity after a certain period of time. The conclusion is that the Cox hazard ratio is not causally interpretable as a hazard ratio unless there is no treatment effect or an untestable and unrealistic assumption holds. We give a hazard ratio that has a causal interpretation and study its relationship to the Cox hazard ratio.",

author = "Torben Martinussen",

year = "2022",

doi = "10.1146/annurev-statistics-040320-114441",

language = "English",

volume = "9",

pages = "249--259",

journal = "Annual Review of Statistics and Its Application",

issn = "2326-8298",

publisher = "Annual Reviews, inc.",

}

RIS

TY - JOUR

T1 - Causality and the Cox Regression Model

AU - Martinussen, Torben

PY - 2022

Y1 - 2022

N2 - This article surveys results concerning the interpretation of the Cox hazard ratio in connection to causality in a randomized study with a time-To-event response. The Cox model is assumed to be correctly specified, and we investigate whether the typical end product of such an analysis, the estimated hazard ratio, has a causal interpretation as a hazard ratio. It has been pointed out that this is not possible due to selection. We provide more insight into the interpretation of hazard ratios and differences, investigating what can be learned about a treatment effect from the hazard ratio approaching unity after a certain period of time. The conclusion is that the Cox hazard ratio is not causally interpretable as a hazard ratio unless there is no treatment effect or an untestable and unrealistic assumption holds. We give a hazard ratio that has a causal interpretation and study its relationship to the Cox hazard ratio.

AB - This article surveys results concerning the interpretation of the Cox hazard ratio in connection to causality in a randomized study with a time-To-event response. The Cox model is assumed to be correctly specified, and we investigate whether the typical end product of such an analysis, the estimated hazard ratio, has a causal interpretation as a hazard ratio. It has been pointed out that this is not possible due to selection. We provide more insight into the interpretation of hazard ratios and differences, investigating what can be learned about a treatment effect from the hazard ratio approaching unity after a certain period of time. The conclusion is that the Cox hazard ratio is not causally interpretable as a hazard ratio unless there is no treatment effect or an untestable and unrealistic assumption holds. We give a hazard ratio that has a causal interpretation and study its relationship to the Cox hazard ratio.

U2 - 10.1146/annurev-statistics-040320-114441

DO - 10.1146/annurev-statistics-040320-114441

M3 - Journal article

AN - SCOPUS:85126558013

VL - 9

SP - 249

EP - 259

JO - Annual Review of Statistics and Its Application

JF - Annual Review of Statistics and Its Application

SN - 2326-8298

ER -

ID: 302403967