Global effects estimation for multidimensional outcomes

T. G. Travison, R. Brookmeyer

Research output: Contribution to journalArticle

Abstract

Many health studies focus on multifaceted outcomes that are not easily measured with a single variable; examples include studies on quality of life (QOL) and general health. To fully explore such an outcome, researchers typically collect information on multiple endpoints. The resulting measurements constitute multidimensional outcome data. An object of great interest is the overall-or global-effect of a covariate, such as a treatment intervention, on the multidimensional outcome. Quantifying such an effect can be difficult because multiple clinical outcomes are usually measured on different scales; the problem is enhanced by the fact that multiple measurements on a given subject are typically correlated. We present a regression modeling scheme permitting estimation of global treatment effects when multiple continuous endpoints are examined in concert either once or for several times. The global effect is conceptualized as a change in the distribution functions of the outcome variables. It may thus be interpreted as a connection between outcome distribution quantiles for the treatment and control groups. This concept allows the presentation of a global effect as a scalar quantity applicable to all outcomes simultaneously, easing interpretation of results. Model estimation proceeds directly from existing methods for multivariate survival analysis. The assumption that the treatment effect is homogenous across different outcomes is testable. To illustrate the application, we present data analytic results from a motivating example, an analysis of patients' QOL during recovery from lower limb trauma. We also explore the performance properties of global effects estimation through simulation.

Original languageEnglish (US)
Pages (from-to)4845-4859
Number of pages15
JournalStatistics in Medicine
Volume26
Issue number27
DOIs
StatePublished - Nov 30 2007

Fingerprint

Quality of Life
Health
Therapeutics
Survival Analysis
Treatment Effects
Lower Extremity
Multivariate Analysis
Research Personnel
Multiple Endpoints
Control Groups
Wounds and Injuries
Quantile
Covariates
Distribution Function
Recovery
Regression
Scalar
Modeling
Simulation
Model

Keywords

  • Marginal model
  • Multivariate
  • Ranks
  • Treatment effect

ASJC Scopus subject areas

  • Epidemiology

Cite this

Global effects estimation for multidimensional outcomes. / Travison, T. G.; Brookmeyer, R.

In: Statistics in Medicine, Vol. 26, No. 27, 30.11.2007, p. 4845-4859.

Research output: Contribution to journalArticle

Travison, TG & Brookmeyer, R 2007, 'Global effects estimation for multidimensional outcomes', Statistics in Medicine, vol. 26, no. 27, pp. 4845-4859. https://doi.org/10.1002/sim.2983
Travison, T. G. ; Brookmeyer, R. / Global effects estimation for multidimensional outcomes. In: Statistics in Medicine. 2007 ; Vol. 26, No. 27. pp. 4845-4859.
@article{51911a0bbfea4f0eb8ad9dea61f01a53,
title = "Global effects estimation for multidimensional outcomes",
abstract = "Many health studies focus on multifaceted outcomes that are not easily measured with a single variable; examples include studies on quality of life (QOL) and general health. To fully explore such an outcome, researchers typically collect information on multiple endpoints. The resulting measurements constitute multidimensional outcome data. An object of great interest is the overall-or global-effect of a covariate, such as a treatment intervention, on the multidimensional outcome. Quantifying such an effect can be difficult because multiple clinical outcomes are usually measured on different scales; the problem is enhanced by the fact that multiple measurements on a given subject are typically correlated. We present a regression modeling scheme permitting estimation of global treatment effects when multiple continuous endpoints are examined in concert either once or for several times. The global effect is conceptualized as a change in the distribution functions of the outcome variables. It may thus be interpreted as a connection between outcome distribution quantiles for the treatment and control groups. This concept allows the presentation of a global effect as a scalar quantity applicable to all outcomes simultaneously, easing interpretation of results. Model estimation proceeds directly from existing methods for multivariate survival analysis. The assumption that the treatment effect is homogenous across different outcomes is testable. To illustrate the application, we present data analytic results from a motivating example, an analysis of patients' QOL during recovery from lower limb trauma. We also explore the performance properties of global effects estimation through simulation.",
keywords = "Marginal model, Multivariate, Ranks, Treatment effect",
author = "Travison, {T. G.} and R. Brookmeyer",
year = "2007",
month = "11",
day = "30",
doi = "10.1002/sim.2983",
language = "English (US)",
volume = "26",
pages = "4845--4859",
journal = "Statistics in Medicine",
issn = "0277-6715",
publisher = "John Wiley and Sons Ltd",
number = "27",

}

TY - JOUR

T1 - Global effects estimation for multidimensional outcomes

AU - Travison, T. G.

AU - Brookmeyer, R.

PY - 2007/11/30

Y1 - 2007/11/30

N2 - Many health studies focus on multifaceted outcomes that are not easily measured with a single variable; examples include studies on quality of life (QOL) and general health. To fully explore such an outcome, researchers typically collect information on multiple endpoints. The resulting measurements constitute multidimensional outcome data. An object of great interest is the overall-or global-effect of a covariate, such as a treatment intervention, on the multidimensional outcome. Quantifying such an effect can be difficult because multiple clinical outcomes are usually measured on different scales; the problem is enhanced by the fact that multiple measurements on a given subject are typically correlated. We present a regression modeling scheme permitting estimation of global treatment effects when multiple continuous endpoints are examined in concert either once or for several times. The global effect is conceptualized as a change in the distribution functions of the outcome variables. It may thus be interpreted as a connection between outcome distribution quantiles for the treatment and control groups. This concept allows the presentation of a global effect as a scalar quantity applicable to all outcomes simultaneously, easing interpretation of results. Model estimation proceeds directly from existing methods for multivariate survival analysis. The assumption that the treatment effect is homogenous across different outcomes is testable. To illustrate the application, we present data analytic results from a motivating example, an analysis of patients' QOL during recovery from lower limb trauma. We also explore the performance properties of global effects estimation through simulation.

AB - Many health studies focus on multifaceted outcomes that are not easily measured with a single variable; examples include studies on quality of life (QOL) and general health. To fully explore such an outcome, researchers typically collect information on multiple endpoints. The resulting measurements constitute multidimensional outcome data. An object of great interest is the overall-or global-effect of a covariate, such as a treatment intervention, on the multidimensional outcome. Quantifying such an effect can be difficult because multiple clinical outcomes are usually measured on different scales; the problem is enhanced by the fact that multiple measurements on a given subject are typically correlated. We present a regression modeling scheme permitting estimation of global treatment effects when multiple continuous endpoints are examined in concert either once or for several times. The global effect is conceptualized as a change in the distribution functions of the outcome variables. It may thus be interpreted as a connection between outcome distribution quantiles for the treatment and control groups. This concept allows the presentation of a global effect as a scalar quantity applicable to all outcomes simultaneously, easing interpretation of results. Model estimation proceeds directly from existing methods for multivariate survival analysis. The assumption that the treatment effect is homogenous across different outcomes is testable. To illustrate the application, we present data analytic results from a motivating example, an analysis of patients' QOL during recovery from lower limb trauma. We also explore the performance properties of global effects estimation through simulation.

KW - Marginal model

KW - Multivariate

KW - Ranks

KW - Treatment effect

UR - http://www.scopus.com/inward/record.url?scp=35948978913&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=35948978913&partnerID=8YFLogxK

U2 - 10.1002/sim.2983

DO - 10.1002/sim.2983

M3 - Article

C2 - 17619238

AN - SCOPUS:35948978913

VL - 26

SP - 4845

EP - 4859

JO - Statistics in Medicine

JF - Statistics in Medicine

SN - 0277-6715

IS - 27

ER -