Nonsmooth backfitting for the excess risk additive regression model with two survival time scales

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

Standard

Nonsmooth backfitting for the excess risk additive regression model with two survival time scales. / Hiabu, M.; Nielsen, J. P.; Scheike, T. H.

In: Biometrika, Vol. 108, No. 2, 2021, p. 491-506.

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

Harvard

Hiabu, M, Nielsen, JP & Scheike, TH 2021, 'Nonsmooth backfitting for the excess risk additive regression model with two survival time scales', Biometrika, vol. 108, no. 2, pp. 491-506. https://doi.org/10.1093/biomet/asaa058

APA

Hiabu, M., Nielsen, J. P., & Scheike, T. H. (2021). Nonsmooth backfitting for the excess risk additive regression model with two survival time scales. Biometrika, 108(2), 491-506. https://doi.org/10.1093/biomet/asaa058

Vancouver

Hiabu M, Nielsen JP, Scheike TH. Nonsmooth backfitting for the excess risk additive regression model with two survival time scales. Biometrika. 2021;108(2):491-506. https://doi.org/10.1093/biomet/asaa058

Author

Hiabu, M. ; Nielsen, J. P. ; Scheike, T. H. / Nonsmooth backfitting for the excess risk additive regression model with two survival time scales. In: Biometrika. 2021 ; Vol. 108, No. 2. pp. 491-506.

Bibtex

@article{e8481937cab64534a9ad8905918bca14,
title = "Nonsmooth backfitting for the excess risk additive regression model with two survival time scales",
abstract = "We consider an extension of Aalen's additive regression model that allows covariates to have effects that vary on two different time scales. The two time scales considered are equal up to a constant for each individual and vary across individuals, such as follow-up time and age in medical studies or calendar time and age in longitudinal studies. The model was introduced in Scheike (2001), where it was solved using smoothing techniques. We present a new backfitting algorithm for estimating the structured model without having to use smoothing. Estimators of the cumulative regression functions on the two time scales are suggested by solving local estimating equations jointly on the two time scales. We provide large-sample properties and simultaneous confidence bands. The model is applied to data on myocardial infarction, providing a separation of the two effects stemming from time since diagnosis and age.",
keywords = "Aalen model, Counting process, Disability model, Generalized additive model, Illness-death model, Multiple time scale, Nonparametric estimation, Varying-coefficient model, ESTIMATOR",
author = "M. Hiabu and Nielsen, {J. P.} and Scheike, {T. H.}",
year = "2021",
doi = "10.1093/biomet/asaa058",
language = "English",
volume = "108",
pages = "491--506",
journal = "Biometrika",
issn = "0006-3444",
publisher = "Oxford University Press",
number = "2",

}

RIS

TY - JOUR

T1 - Nonsmooth backfitting for the excess risk additive regression model with two survival time scales

AU - Hiabu, M.

AU - Nielsen, J. P.

AU - Scheike, T. H.

PY - 2021

Y1 - 2021

N2 - We consider an extension of Aalen's additive regression model that allows covariates to have effects that vary on two different time scales. The two time scales considered are equal up to a constant for each individual and vary across individuals, such as follow-up time and age in medical studies or calendar time and age in longitudinal studies. The model was introduced in Scheike (2001), where it was solved using smoothing techniques. We present a new backfitting algorithm for estimating the structured model without having to use smoothing. Estimators of the cumulative regression functions on the two time scales are suggested by solving local estimating equations jointly on the two time scales. We provide large-sample properties and simultaneous confidence bands. The model is applied to data on myocardial infarction, providing a separation of the two effects stemming from time since diagnosis and age.

AB - We consider an extension of Aalen's additive regression model that allows covariates to have effects that vary on two different time scales. The two time scales considered are equal up to a constant for each individual and vary across individuals, such as follow-up time and age in medical studies or calendar time and age in longitudinal studies. The model was introduced in Scheike (2001), where it was solved using smoothing techniques. We present a new backfitting algorithm for estimating the structured model without having to use smoothing. Estimators of the cumulative regression functions on the two time scales are suggested by solving local estimating equations jointly on the two time scales. We provide large-sample properties and simultaneous confidence bands. The model is applied to data on myocardial infarction, providing a separation of the two effects stemming from time since diagnosis and age.

KW - Aalen model

KW - Counting process

KW - Disability model

KW - Generalized additive model

KW - Illness-death model

KW - Multiple time scale

KW - Nonparametric estimation

KW - Varying-coefficient model

KW - ESTIMATOR

U2 - 10.1093/biomet/asaa058

DO - 10.1093/biomet/asaa058

M3 - Journal article

VL - 108

SP - 491

EP - 506

JO - Biometrika

JF - Biometrika

SN - 0006-3444

IS - 2

ER -

ID: 273747742