Cox regression survival analysis with compositional covariates: application to modelling mortality risk from 24-hour physical activity patterns

D.E. McGregor, J. Palarea-Albaladejo, P.M. Dall, K. Hron, S.F.M. Chastin

Research output: Contribution to journalArticle

32 Downloads (Pure)

Abstract

Survival analysis is commonly conducted in medical and public health research to assess the association of an exposure or intervention with a hard end outcome such as mortality. The Cox (proportional hazards) regression model is probably the most popular statistical tool used in this context. However, when the exposure includes compositional covariables (that is, variables representing a relative makeup such as a nutritional or physical activity behaviour composition), some basic assumptions of the Cox regression model and associated significance tests are violated. Compositional variables involve an intrinsic interplay between one another which precludes results and conclusions based on considering them in isolation as is ordinarily done. In this work, we introduce a formulation of the Cox regression model in terms of log-ratio coordinates which suitably deals with the constraints of compositional covariates, facilitates the use of common statistical inference methods, and allows for scientifically meaningful interpretations. We illustrate its practical application to a public health problem: the estimation of the mortality hazard associated with the composition of daily activity behaviour (physical activity, sitting time and sleep) using data from the U.S. National Health and Nutrition Examination Survey (NHANES).
Original languageEnglish
JournalStatistical Methods in Medical Research
Early online date25 Jul 2019
DOIs
Publication statusE-pub ahead of print - 25 Jul 2019

Fingerprint

Cox Regression
Survival Analysis
Proportional Hazards Models
Regression Analysis
Mortality
Cox Regression Model
Covariates
Public Health
Modeling
Proportional Hazards Regression
Significance Test
Hazard Models
Nutrition
Nutrition Surveys
Sleep
Statistical Inference
Hazard
Isolation
Regression Model
Health

Keywords

  • survival analysis
  • Cox regression
  • compositional data
  • time use
  • accelerometry
  • physical activity
  • sedentary behaviour
  • NHANES

Cite this

@article{2ac0afa0bc5e4f9eb3bfba9f58dee85f,
title = "Cox regression survival analysis with compositional covariates: application to modelling mortality risk from 24-hour physical activity patterns",
abstract = "Survival analysis is commonly conducted in medical and public health research to assess the association of an exposure or intervention with a hard end outcome such as mortality. The Cox (proportional hazards) regression model is probably the most popular statistical tool used in this context. However, when the exposure includes compositional covariables (that is, variables representing a relative makeup such as a nutritional or physical activity behaviour composition), some basic assumptions of the Cox regression model and associated significance tests are violated. Compositional variables involve an intrinsic interplay between one another which precludes results and conclusions based on considering them in isolation as is ordinarily done. In this work, we introduce a formulation of the Cox regression model in terms of log-ratio coordinates which suitably deals with the constraints of compositional covariates, facilitates the use of common statistical inference methods, and allows for scientifically meaningful interpretations. We illustrate its practical application to a public health problem: the estimation of the mortality hazard associated with the composition of daily activity behaviour (physical activity, sitting time and sleep) using data from the U.S. National Health and Nutrition Examination Survey (NHANES).",
keywords = "survival analysis, Cox regression, compositional data, time use, accelerometry, physical activity, sedentary behaviour, NHANES",
author = "D.E. McGregor and J. Palarea-Albaladejo and P.M. Dall and K. Hron and S.F.M. Chastin",
note = "Acceptance in SAN AAM: no embargo",
year = "2019",
month = "7",
day = "25",
doi = "10.1177/0962280219864125",
language = "English",

}

Cox regression survival analysis with compositional covariates: application to modelling mortality risk from 24-hour physical activity patterns. / McGregor, D.E.; Palarea-Albaladejo, J.; Dall, P.M.; Hron, K.; Chastin, S.F.M.

In: Statistical Methods in Medical Research, 25.07.2019.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Cox regression survival analysis with compositional covariates: application to modelling mortality risk from 24-hour physical activity patterns

AU - McGregor, D.E.

AU - Palarea-Albaladejo, J.

AU - Dall, P.M.

AU - Hron, K.

AU - Chastin, S.F.M.

N1 - Acceptance in SAN AAM: no embargo

PY - 2019/7/25

Y1 - 2019/7/25

N2 - Survival analysis is commonly conducted in medical and public health research to assess the association of an exposure or intervention with a hard end outcome such as mortality. The Cox (proportional hazards) regression model is probably the most popular statistical tool used in this context. However, when the exposure includes compositional covariables (that is, variables representing a relative makeup such as a nutritional or physical activity behaviour composition), some basic assumptions of the Cox regression model and associated significance tests are violated. Compositional variables involve an intrinsic interplay between one another which precludes results and conclusions based on considering them in isolation as is ordinarily done. In this work, we introduce a formulation of the Cox regression model in terms of log-ratio coordinates which suitably deals with the constraints of compositional covariates, facilitates the use of common statistical inference methods, and allows for scientifically meaningful interpretations. We illustrate its practical application to a public health problem: the estimation of the mortality hazard associated with the composition of daily activity behaviour (physical activity, sitting time and sleep) using data from the U.S. National Health and Nutrition Examination Survey (NHANES).

AB - Survival analysis is commonly conducted in medical and public health research to assess the association of an exposure or intervention with a hard end outcome such as mortality. The Cox (proportional hazards) regression model is probably the most popular statistical tool used in this context. However, when the exposure includes compositional covariables (that is, variables representing a relative makeup such as a nutritional or physical activity behaviour composition), some basic assumptions of the Cox regression model and associated significance tests are violated. Compositional variables involve an intrinsic interplay between one another which precludes results and conclusions based on considering them in isolation as is ordinarily done. In this work, we introduce a formulation of the Cox regression model in terms of log-ratio coordinates which suitably deals with the constraints of compositional covariates, facilitates the use of common statistical inference methods, and allows for scientifically meaningful interpretations. We illustrate its practical application to a public health problem: the estimation of the mortality hazard associated with the composition of daily activity behaviour (physical activity, sitting time and sleep) using data from the U.S. National Health and Nutrition Examination Survey (NHANES).

KW - survival analysis

KW - Cox regression

KW - compositional data

KW - time use

KW - accelerometry

KW - physical activity

KW - sedentary behaviour

KW - NHANES

U2 - 10.1177/0962280219864125

DO - 10.1177/0962280219864125

M3 - Article

ER -