Joint modeling of missing data due to non-participation and death in longitudinal aging studies

Kumar Rajan, Sue E. Leurgans

Research output: Contribution to journalArticle

10 Citations (Scopus)

Abstract

Specific age-related hypotheses are tested in population-based longitudinal studies. At specific time intervals, both the outcomes of interest and the time-varying covariates are measured. When participants are approached for follow-up, some participants do not provide data. Investigations may show that many have died before the time of follow-up whereas others refused to participate. Some of these non-participants do not provide data at later follow-ups. Few statistical methods for missing data distinguish between 'non-participation' and 'death' among study participants. The augmented inverse probability-weighted estimators are most commonly used in marginal structure models when data are missing at random. Treating non-participation and death as the same, however, may lead to biased estimates and invalid inferences. To overcome this limitation, a multiple inverse probability-weighted approach is presented to account for two types of missing data, non-participation and death, when using a marginal mean model. Under certain conditions, the multiple weighted estimators are consistent and asymptotically normal. Simulation studies will be used to study the finite sample efficiency of the multiple weighted estimators. The proposed method will be applied to study the risk factors associated with the cognitive decline among the aging adults, using data from the Chicago Health and Aging Project (CHAP).

Original languageEnglish (US)
Pages (from-to)2260-2268
Number of pages9
JournalStatistics in Medicine
Volume29
Issue number21
DOIs
StatePublished - Sep 20 2010
Externally publishedYes

Fingerprint

Joint Modeling
Missing Data
Longitudinal Studies
Joints
Estimator
Time-varying Covariates
Missing at Random
Longitudinal Study
Risk Factors
Statistical method
Data Model
Biased
Health
Simulation Study
Interval
Estimate
Population
Model

Keywords

  • Missing data
  • Missing due to death
  • Weighted regression

ASJC Scopus subject areas

  • Epidemiology
  • Statistics and Probability

Cite this

Joint modeling of missing data due to non-participation and death in longitudinal aging studies. / Rajan, Kumar; Leurgans, Sue E.

In: Statistics in Medicine, Vol. 29, No. 21, 20.09.2010, p. 2260-2268.

Research output: Contribution to journalArticle

@article{ec1037cd45aa40a2825b70a7ab09cd26,
title = "Joint modeling of missing data due to non-participation and death in longitudinal aging studies",
abstract = "Specific age-related hypotheses are tested in population-based longitudinal studies. At specific time intervals, both the outcomes of interest and the time-varying covariates are measured. When participants are approached for follow-up, some participants do not provide data. Investigations may show that many have died before the time of follow-up whereas others refused to participate. Some of these non-participants do not provide data at later follow-ups. Few statistical methods for missing data distinguish between 'non-participation' and 'death' among study participants. The augmented inverse probability-weighted estimators are most commonly used in marginal structure models when data are missing at random. Treating non-participation and death as the same, however, may lead to biased estimates and invalid inferences. To overcome this limitation, a multiple inverse probability-weighted approach is presented to account for two types of missing data, non-participation and death, when using a marginal mean model. Under certain conditions, the multiple weighted estimators are consistent and asymptotically normal. Simulation studies will be used to study the finite sample efficiency of the multiple weighted estimators. The proposed method will be applied to study the risk factors associated with the cognitive decline among the aging adults, using data from the Chicago Health and Aging Project (CHAP).",
keywords = "Missing data, Missing due to death, Weighted regression",
author = "Kumar Rajan and Leurgans, {Sue E.}",
year = "2010",
month = "9",
day = "20",
doi = "10.1002/sim.4010",
language = "English (US)",
volume = "29",
pages = "2260--2268",
journal = "Statistics in Medicine",
issn = "0277-6715",
publisher = "John Wiley and Sons Ltd",
number = "21",

}

TY - JOUR

T1 - Joint modeling of missing data due to non-participation and death in longitudinal aging studies

AU - Rajan, Kumar

AU - Leurgans, Sue E.

PY - 2010/9/20

Y1 - 2010/9/20

N2 - Specific age-related hypotheses are tested in population-based longitudinal studies. At specific time intervals, both the outcomes of interest and the time-varying covariates are measured. When participants are approached for follow-up, some participants do not provide data. Investigations may show that many have died before the time of follow-up whereas others refused to participate. Some of these non-participants do not provide data at later follow-ups. Few statistical methods for missing data distinguish between 'non-participation' and 'death' among study participants. The augmented inverse probability-weighted estimators are most commonly used in marginal structure models when data are missing at random. Treating non-participation and death as the same, however, may lead to biased estimates and invalid inferences. To overcome this limitation, a multiple inverse probability-weighted approach is presented to account for two types of missing data, non-participation and death, when using a marginal mean model. Under certain conditions, the multiple weighted estimators are consistent and asymptotically normal. Simulation studies will be used to study the finite sample efficiency of the multiple weighted estimators. The proposed method will be applied to study the risk factors associated with the cognitive decline among the aging adults, using data from the Chicago Health and Aging Project (CHAP).

AB - Specific age-related hypotheses are tested in population-based longitudinal studies. At specific time intervals, both the outcomes of interest and the time-varying covariates are measured. When participants are approached for follow-up, some participants do not provide data. Investigations may show that many have died before the time of follow-up whereas others refused to participate. Some of these non-participants do not provide data at later follow-ups. Few statistical methods for missing data distinguish between 'non-participation' and 'death' among study participants. The augmented inverse probability-weighted estimators are most commonly used in marginal structure models when data are missing at random. Treating non-participation and death as the same, however, may lead to biased estimates and invalid inferences. To overcome this limitation, a multiple inverse probability-weighted approach is presented to account for two types of missing data, non-participation and death, when using a marginal mean model. Under certain conditions, the multiple weighted estimators are consistent and asymptotically normal. Simulation studies will be used to study the finite sample efficiency of the multiple weighted estimators. The proposed method will be applied to study the risk factors associated with the cognitive decline among the aging adults, using data from the Chicago Health and Aging Project (CHAP).

KW - Missing data

KW - Missing due to death

KW - Weighted regression

UR - http://www.scopus.com/inward/record.url?scp=77956931028&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77956931028&partnerID=8YFLogxK

U2 - 10.1002/sim.4010

DO - 10.1002/sim.4010

M3 - Article

VL - 29

SP - 2260

EP - 2268

JO - Statistics in Medicine

JF - Statistics in Medicine

SN - 0277-6715

IS - 21

ER -