Causal inference for non-mortality outcomes in the presence of death

Brian L. Egleston, Daniel O Scharfstein, Ellen E. Freeman, Sheila K West

Research output: Contribution to journalArticle

Abstract

Evaluation of the causal effect of a baseline exposure on a morbidity outcome at a fixed time point is often complicated when study participants die before morbidity outcomes are measured. In this setting, the causal effect is only well defined for the principal stratum of subjects who would live regardless of the exposure. Motivated by gerontologic researchers interested in understanding the causal effect of vision loss on emotional distress in a population with a high mortality rate, we investigate the effect among those who would live both with and without vision loss. Since this subpopulation is not readily identifiable from the data and vision loss is not randomized, we introduce a set of scientifically driven assumptions to identify the causal effect. Since these assumptions are not empirically verifiable, we embed our methodology within a sensitivity analysis framework. We apply our method using the first three rounds of survey data from the Salisbury Eye Evaluation, a population-based cohort study of older adults. We also present a simulation study that validates our method.

Original languageEnglish (US)
Pages (from-to)526-545
Number of pages20
JournalBiostatistics
Volume8
Issue number3
DOIs
StatePublished - Jul 2007

Fingerprint

Causal Inference
Causal Effect
Morbidity
Cohort Study
Population
Mortality Rate
Survey Data
Evaluation
Cohort Studies
Research Personnel
Sensitivity Analysis
Well-defined
Baseline
Die
Mortality
Simulation Study
Causal inference
Causal effect
Methodology
Vision

Keywords

  • Causal inference
  • Competing risk
  • Emotional distress
  • Sensitivity analysis
  • Vision loss

ASJC Scopus subject areas

  • Medicine(all)
  • Statistics and Probability
  • Statistics, Probability and Uncertainty

Cite this

Causal inference for non-mortality outcomes in the presence of death. / Egleston, Brian L.; Scharfstein, Daniel O; Freeman, Ellen E.; West, Sheila K.

In: Biostatistics, Vol. 8, No. 3, 07.2007, p. 526-545.

Research output: Contribution to journalArticle

Egleston, Brian L. ; Scharfstein, Daniel O ; Freeman, Ellen E. ; West, Sheila K. / Causal inference for non-mortality outcomes in the presence of death. In: Biostatistics. 2007 ; Vol. 8, No. 3. pp. 526-545.
@article{946ae50e50d34f50a86c625afd17edf5,
title = "Causal inference for non-mortality outcomes in the presence of death",
abstract = "Evaluation of the causal effect of a baseline exposure on a morbidity outcome at a fixed time point is often complicated when study participants die before morbidity outcomes are measured. In this setting, the causal effect is only well defined for the principal stratum of subjects who would live regardless of the exposure. Motivated by gerontologic researchers interested in understanding the causal effect of vision loss on emotional distress in a population with a high mortality rate, we investigate the effect among those who would live both with and without vision loss. Since this subpopulation is not readily identifiable from the data and vision loss is not randomized, we introduce a set of scientifically driven assumptions to identify the causal effect. Since these assumptions are not empirically verifiable, we embed our methodology within a sensitivity analysis framework. We apply our method using the first three rounds of survey data from the Salisbury Eye Evaluation, a population-based cohort study of older adults. We also present a simulation study that validates our method.",
keywords = "Causal inference, Competing risk, Emotional distress, Sensitivity analysis, Vision loss",
author = "Egleston, {Brian L.} and Scharfstein, {Daniel O} and Freeman, {Ellen E.} and West, {Sheila K}",
year = "2007",
month = "7",
doi = "10.1093/biostatistics/kxl027",
language = "English (US)",
volume = "8",
pages = "526--545",
journal = "Biostatistics",
issn = "1465-4644",
publisher = "Oxford University Press",
number = "3",

}

TY - JOUR

T1 - Causal inference for non-mortality outcomes in the presence of death

AU - Egleston, Brian L.

AU - Scharfstein, Daniel O

AU - Freeman, Ellen E.

AU - West, Sheila K

PY - 2007/7

Y1 - 2007/7

N2 - Evaluation of the causal effect of a baseline exposure on a morbidity outcome at a fixed time point is often complicated when study participants die before morbidity outcomes are measured. In this setting, the causal effect is only well defined for the principal stratum of subjects who would live regardless of the exposure. Motivated by gerontologic researchers interested in understanding the causal effect of vision loss on emotional distress in a population with a high mortality rate, we investigate the effect among those who would live both with and without vision loss. Since this subpopulation is not readily identifiable from the data and vision loss is not randomized, we introduce a set of scientifically driven assumptions to identify the causal effect. Since these assumptions are not empirically verifiable, we embed our methodology within a sensitivity analysis framework. We apply our method using the first three rounds of survey data from the Salisbury Eye Evaluation, a population-based cohort study of older adults. We also present a simulation study that validates our method.

AB - Evaluation of the causal effect of a baseline exposure on a morbidity outcome at a fixed time point is often complicated when study participants die before morbidity outcomes are measured. In this setting, the causal effect is only well defined for the principal stratum of subjects who would live regardless of the exposure. Motivated by gerontologic researchers interested in understanding the causal effect of vision loss on emotional distress in a population with a high mortality rate, we investigate the effect among those who would live both with and without vision loss. Since this subpopulation is not readily identifiable from the data and vision loss is not randomized, we introduce a set of scientifically driven assumptions to identify the causal effect. Since these assumptions are not empirically verifiable, we embed our methodology within a sensitivity analysis framework. We apply our method using the first three rounds of survey data from the Salisbury Eye Evaluation, a population-based cohort study of older adults. We also present a simulation study that validates our method.

KW - Causal inference

KW - Competing risk

KW - Emotional distress

KW - Sensitivity analysis

KW - Vision loss

UR - http://www.scopus.com/inward/record.url?scp=34648843641&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34648843641&partnerID=8YFLogxK

U2 - 10.1093/biostatistics/kxl027

DO - 10.1093/biostatistics/kxl027

M3 - Article

C2 - 16980696

AN - SCOPUS:34648843641

VL - 8

SP - 526

EP - 545

JO - Biostatistics

JF - Biostatistics

SN - 1465-4644

IS - 3

ER -