By the same authors

From the same journal

From the same journal

Generalised linear models for flexible parametric modelling of the hazard function

Research output: Contribution to journalArticle

Standard

Generalised linear models for flexible parametric modelling of the hazard function. / Kearns, Benjamin; Stevenson, Matt; Triantafyllopoulos, Kostas; Manca, Andrea.

In: Medical Decision Making, 23.07.2019.

Research output: Contribution to journalArticle

Harvard

Kearns, B, Stevenson, M, Triantafyllopoulos, K & Manca, A 2019, 'Generalised linear models for flexible parametric modelling of the hazard function', Medical Decision Making.

APA

Kearns, B., Stevenson, M., Triantafyllopoulos, K., & Manca, A. (Accepted/In press). Generalised linear models for flexible parametric modelling of the hazard function. Medical Decision Making.

Vancouver

Kearns B, Stevenson M, Triantafyllopoulos K, Manca A. Generalised linear models for flexible parametric modelling of the hazard function. Medical Decision Making. 2019 Jul 23.

Author

Kearns, Benjamin ; Stevenson, Matt ; Triantafyllopoulos, Kostas ; Manca, Andrea. / Generalised linear models for flexible parametric modelling of the hazard function. In: Medical Decision Making. 2019.

Bibtex - Download

@article{163c1d0442684f4fb8b90031d24dafff,
title = "Generalised linear models for flexible parametric modelling of the hazard function",
abstract = "Background: Parametric modelling of survival data is important and reimbursement decisions may depend on the selected distribution. Accurate predictions require sufficiently flexible models to describe adequately the temporal evolution of the hazard function. A rich class of models is available among the framework of generalised linear models (GLMs) and its extensions, but these models are rarely applied to survival data. This manuscript describes the theoretical properties of these more flexible models, and compares their performance to standard survival models in a reproducible case-study.Methods: We describe how survival data may be analysed with GLMs and its extensions: fractional polynomials, spline models, generalised additive models, generalised linear mixed (frailty) models and dynamic survival models. For each, we provide a comparison of the strengths and limitations of these approaches. For the case-study we compare within-sample t, the plausibility of extrapolations and extrapolation performance based on data-splitting. Results: Viewing standard survival models as GLMs shows that many impose a restrictive assumption of linearity. For the case-study, GLMs provided better within-sample t and more plausible extrapolations. However, they did not improve extrapolation performance. We also provide guidance to aid in choosing between the different approaches based on GLMs and its extensions.Conclusions: The use of GLMs for parametric survival analysis can out-perform standard parametric survival models, although the improvements were modest in our case-study. This approach is currently seldom used. We provide guidance on both implementing these models and choosing between them. The reproducible case-study will help to increase uptake of these models.",
author = "Benjamin Kearns and Matt Stevenson and Kostas Triantafyllopoulos and Andrea Manca",
note = "{\circledC} 2019. The Author(s). This is an author-produced version of the published paper. Uploaded in accordance with the publisher’s self-archiving policy. Further copying may not be permitted; contact the publisher for details.",
year = "2019",
month = "7",
day = "23",
language = "English",
journal = "Medical Decision Making",
issn = "0272-989X",
publisher = "SAGE Publications",

}

RIS (suitable for import to EndNote) - Download

TY - JOUR

T1 - Generalised linear models for flexible parametric modelling of the hazard function

AU - Kearns, Benjamin

AU - Stevenson, Matt

AU - Triantafyllopoulos, Kostas

AU - Manca, Andrea

N1 - © 2019. The Author(s). This is an author-produced version of the published paper. Uploaded in accordance with the publisher’s self-archiving policy. Further copying may not be permitted; contact the publisher for details.

PY - 2019/7/23

Y1 - 2019/7/23

N2 - Background: Parametric modelling of survival data is important and reimbursement decisions may depend on the selected distribution. Accurate predictions require sufficiently flexible models to describe adequately the temporal evolution of the hazard function. A rich class of models is available among the framework of generalised linear models (GLMs) and its extensions, but these models are rarely applied to survival data. This manuscript describes the theoretical properties of these more flexible models, and compares their performance to standard survival models in a reproducible case-study.Methods: We describe how survival data may be analysed with GLMs and its extensions: fractional polynomials, spline models, generalised additive models, generalised linear mixed (frailty) models and dynamic survival models. For each, we provide a comparison of the strengths and limitations of these approaches. For the case-study we compare within-sample t, the plausibility of extrapolations and extrapolation performance based on data-splitting. Results: Viewing standard survival models as GLMs shows that many impose a restrictive assumption of linearity. For the case-study, GLMs provided better within-sample t and more plausible extrapolations. However, they did not improve extrapolation performance. We also provide guidance to aid in choosing between the different approaches based on GLMs and its extensions.Conclusions: The use of GLMs for parametric survival analysis can out-perform standard parametric survival models, although the improvements were modest in our case-study. This approach is currently seldom used. We provide guidance on both implementing these models and choosing between them. The reproducible case-study will help to increase uptake of these models.

AB - Background: Parametric modelling of survival data is important and reimbursement decisions may depend on the selected distribution. Accurate predictions require sufficiently flexible models to describe adequately the temporal evolution of the hazard function. A rich class of models is available among the framework of generalised linear models (GLMs) and its extensions, but these models are rarely applied to survival data. This manuscript describes the theoretical properties of these more flexible models, and compares their performance to standard survival models in a reproducible case-study.Methods: We describe how survival data may be analysed with GLMs and its extensions: fractional polynomials, spline models, generalised additive models, generalised linear mixed (frailty) models and dynamic survival models. For each, we provide a comparison of the strengths and limitations of these approaches. For the case-study we compare within-sample t, the plausibility of extrapolations and extrapolation performance based on data-splitting. Results: Viewing standard survival models as GLMs shows that many impose a restrictive assumption of linearity. For the case-study, GLMs provided better within-sample t and more plausible extrapolations. However, they did not improve extrapolation performance. We also provide guidance to aid in choosing between the different approaches based on GLMs and its extensions.Conclusions: The use of GLMs for parametric survival analysis can out-perform standard parametric survival models, although the improvements were modest in our case-study. This approach is currently seldom used. We provide guidance on both implementing these models and choosing between them. The reproducible case-study will help to increase uptake of these models.

M3 - Article

JO - Medical Decision Making

T2 - Medical Decision Making

JF - Medical Decision Making

SN - 0272-989X

ER -