A mixed-effects model for cognitive decline with non-monotone non-response from a two-phase longitudinal study of dementia

Changyu Shen, Sujuan Gao

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

Most longitudinal studies of elderly are characterized by substantial drop-out due to death and many other factors beyond the control of the investigators. In a two-phase longitudinal study of dementia, subjects with cognitive impairment skip the first phase survey in the next follow-up, leading to intermittent missing variables measured in that phase. In the context of analysing pre-dementia cognitive decline in an elderly population, both of the two causes of non-response can potentially be informative in the sense that the missingness is dependent on the unobserved outcome. To take these factors into account, mixed-effects models are constructed to allow the outcome and the multiple causes of missing values to share the same 'random parameter' or random effect. The crucial assumption of our model is that the random effects of the model for the outcome and that of the model for the missing-data indicators are linked in a deterministic manner. It can be thought of as an approximation of a more general and realistic situation, in which the two models have distinct, yet dependent, random effects. We conduct a simulation study to investigate possible deviations of the estimates under such a scenario. A second simulation illustrates the magnitude of the bias in estimating the difference of decline rate between two groups when the random effects are linked in different manners for the two groups.

Original languageEnglish
Pages (from-to)409-425
Number of pages17
JournalStatistics in Medicine
Volume26
Issue number2
DOIs
StatePublished - Jan 30 2007

Fingerprint

Mixed Effects Model
Dementia
Non-response
Longitudinal Study
Random Effects
Longitudinal Studies
Research Personnel
Random Parameters
Dependent
Drop out
Missing Values
Missing Data
Model
Population
Deviation
Simulation Study
Distinct
Scenarios
Cognitive Dysfunction
Approximation

Keywords

  • Mixed-effects
  • Non-ignorable
  • Non-response
  • Shared parameter
  • Two-phase design

ASJC Scopus subject areas

  • Epidemiology

Cite this

A mixed-effects model for cognitive decline with non-monotone non-response from a two-phase longitudinal study of dementia. / Shen, Changyu; Gao, Sujuan.

In: Statistics in Medicine, Vol. 26, No. 2, 30.01.2007, p. 409-425.

Research output: Contribution to journalArticle

@article{54f5b1d9695247ec8ea073f8828ecb61,
title = "A mixed-effects model for cognitive decline with non-monotone non-response from a two-phase longitudinal study of dementia",
abstract = "Most longitudinal studies of elderly are characterized by substantial drop-out due to death and many other factors beyond the control of the investigators. In a two-phase longitudinal study of dementia, subjects with cognitive impairment skip the first phase survey in the next follow-up, leading to intermittent missing variables measured in that phase. In the context of analysing pre-dementia cognitive decline in an elderly population, both of the two causes of non-response can potentially be informative in the sense that the missingness is dependent on the unobserved outcome. To take these factors into account, mixed-effects models are constructed to allow the outcome and the multiple causes of missing values to share the same 'random parameter' or random effect. The crucial assumption of our model is that the random effects of the model for the outcome and that of the model for the missing-data indicators are linked in a deterministic manner. It can be thought of as an approximation of a more general and realistic situation, in which the two models have distinct, yet dependent, random effects. We conduct a simulation study to investigate possible deviations of the estimates under such a scenario. A second simulation illustrates the magnitude of the bias in estimating the difference of decline rate between two groups when the random effects are linked in different manners for the two groups.",
keywords = "Mixed-effects, Non-ignorable, Non-response, Shared parameter, Two-phase design",
author = "Changyu Shen and Sujuan Gao",
year = "2007",
month = "1",
day = "30",
doi = "10.1002/sim.2454",
language = "English",
volume = "26",
pages = "409--425",
journal = "Statistics in Medicine",
issn = "0277-6715",
publisher = "John Wiley and Sons Ltd",
number = "2",

}

TY - JOUR

T1 - A mixed-effects model for cognitive decline with non-monotone non-response from a two-phase longitudinal study of dementia

AU - Shen, Changyu

AU - Gao, Sujuan

PY - 2007/1/30

Y1 - 2007/1/30

N2 - Most longitudinal studies of elderly are characterized by substantial drop-out due to death and many other factors beyond the control of the investigators. In a two-phase longitudinal study of dementia, subjects with cognitive impairment skip the first phase survey in the next follow-up, leading to intermittent missing variables measured in that phase. In the context of analysing pre-dementia cognitive decline in an elderly population, both of the two causes of non-response can potentially be informative in the sense that the missingness is dependent on the unobserved outcome. To take these factors into account, mixed-effects models are constructed to allow the outcome and the multiple causes of missing values to share the same 'random parameter' or random effect. The crucial assumption of our model is that the random effects of the model for the outcome and that of the model for the missing-data indicators are linked in a deterministic manner. It can be thought of as an approximation of a more general and realistic situation, in which the two models have distinct, yet dependent, random effects. We conduct a simulation study to investigate possible deviations of the estimates under such a scenario. A second simulation illustrates the magnitude of the bias in estimating the difference of decline rate between two groups when the random effects are linked in different manners for the two groups.

AB - Most longitudinal studies of elderly are characterized by substantial drop-out due to death and many other factors beyond the control of the investigators. In a two-phase longitudinal study of dementia, subjects with cognitive impairment skip the first phase survey in the next follow-up, leading to intermittent missing variables measured in that phase. In the context of analysing pre-dementia cognitive decline in an elderly population, both of the two causes of non-response can potentially be informative in the sense that the missingness is dependent on the unobserved outcome. To take these factors into account, mixed-effects models are constructed to allow the outcome and the multiple causes of missing values to share the same 'random parameter' or random effect. The crucial assumption of our model is that the random effects of the model for the outcome and that of the model for the missing-data indicators are linked in a deterministic manner. It can be thought of as an approximation of a more general and realistic situation, in which the two models have distinct, yet dependent, random effects. We conduct a simulation study to investigate possible deviations of the estimates under such a scenario. A second simulation illustrates the magnitude of the bias in estimating the difference of decline rate between two groups when the random effects are linked in different manners for the two groups.

KW - Mixed-effects

KW - Non-ignorable

KW - Non-response

KW - Shared parameter

KW - Two-phase design

UR - http://www.scopus.com/inward/record.url?scp=33846228373&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33846228373&partnerID=8YFLogxK

U2 - 10.1002/sim.2454

DO - 10.1002/sim.2454

M3 - Article

C2 - 16345034

AN - SCOPUS:33846228373

VL - 26

SP - 409

EP - 425

JO - Statistics in Medicine

JF - Statistics in Medicine

SN - 0277-6715

IS - 2

ER -