Multi-stage transitional models with random effects and their application to the Einstein aging study

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

Longitudinal studies of aging often gather repeated observations of cognitive status to describe the development of dementia and to assess the influence of risk factors. Clinical progression to dementia is often conceptualized by a multi-stage model of several transitions that synthesizes time-varying effects. In this study, we assess the influence of risk factors on the transitions among three cognitive status: cognitive stability (normal cognition for age), memory impairment, and clinical dementia. We have developed a shared random effects model that not only links the propensity of transitions and to the probability of informative missingness due to death, but also incorporates heterogeneous transition between subjects. We evaluate four approaches using generalized logit and four using proportional odds models to the first-order Markov transition probabilities as a function of covariates. Random effects were incorporated into these models to account for within-subject correlations. Data from the Einstein Aging Study are used to evaluate the goodness-of-fit of these models using the Akaike information criterion. The best fitting model for each type (generalized logit and proportional odds) is recommended and their results are discussed in more details.

Original languageEnglish (US)
Pages (from-to)938-955
Number of pages18
JournalBiometrical Journal
Volume53
Issue number6
DOIs
StatePublished - Nov 2011

Fingerprint

Multistage Model
Random Effects
Dementia
Albert Einstein
Logit
Risk Factors
Proportional Odds
Proportional Odds Model
Cognition
Akaike Information Criterion
Longitudinal Studies
Evaluate
Longitudinal Study
Random Effects Model
Model Fitting
Goodness of fit
Transition Probability
Progression
Covariates
Time-varying

Keywords

  • Generalized logit
  • Multi-stage
  • Proportional odds
  • Random effects
  • Transition

ASJC Scopus subject areas

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

Cite this

Multi-stage transitional models with random effects and their application to the Einstein aging study. / Song, Changhong; Kuo, Lynn; Derby, Carol A.; Lipton, Richard B.; Hall, Charles B.

In: Biometrical Journal, Vol. 53, No. 6, 11.2011, p. 938-955.

Research output: Contribution to journalArticle

@article{b0606aaf265b484aac322e188199129a,
title = "Multi-stage transitional models with random effects and their application to the Einstein aging study",
abstract = "Longitudinal studies of aging often gather repeated observations of cognitive status to describe the development of dementia and to assess the influence of risk factors. Clinical progression to dementia is often conceptualized by a multi-stage model of several transitions that synthesizes time-varying effects. In this study, we assess the influence of risk factors on the transitions among three cognitive status: cognitive stability (normal cognition for age), memory impairment, and clinical dementia. We have developed a shared random effects model that not only links the propensity of transitions and to the probability of informative missingness due to death, but also incorporates heterogeneous transition between subjects. We evaluate four approaches using generalized logit and four using proportional odds models to the first-order Markov transition probabilities as a function of covariates. Random effects were incorporated into these models to account for within-subject correlations. Data from the Einstein Aging Study are used to evaluate the goodness-of-fit of these models using the Akaike information criterion. The best fitting model for each type (generalized logit and proportional odds) is recommended and their results are discussed in more details.",
keywords = "Generalized logit, Multi-stage, Proportional odds, Random effects, Transition",
author = "Changhong Song and Lynn Kuo and Derby, {Carol A.} and Lipton, {Richard B.} and Hall, {Charles B.}",
year = "2011",
month = "11",
doi = "10.1002/bimj.200900259",
language = "English (US)",
volume = "53",
pages = "938--955",
journal = "Biometrical Journal",
issn = "0323-3847",
publisher = "Wiley-VCH Verlag",
number = "6",

}

TY - JOUR

T1 - Multi-stage transitional models with random effects and their application to the Einstein aging study

AU - Song, Changhong

AU - Kuo, Lynn

AU - Derby, Carol A.

AU - Lipton, Richard B.

AU - Hall, Charles B.

PY - 2011/11

Y1 - 2011/11

N2 - Longitudinal studies of aging often gather repeated observations of cognitive status to describe the development of dementia and to assess the influence of risk factors. Clinical progression to dementia is often conceptualized by a multi-stage model of several transitions that synthesizes time-varying effects. In this study, we assess the influence of risk factors on the transitions among three cognitive status: cognitive stability (normal cognition for age), memory impairment, and clinical dementia. We have developed a shared random effects model that not only links the propensity of transitions and to the probability of informative missingness due to death, but also incorporates heterogeneous transition between subjects. We evaluate four approaches using generalized logit and four using proportional odds models to the first-order Markov transition probabilities as a function of covariates. Random effects were incorporated into these models to account for within-subject correlations. Data from the Einstein Aging Study are used to evaluate the goodness-of-fit of these models using the Akaike information criterion. The best fitting model for each type (generalized logit and proportional odds) is recommended and their results are discussed in more details.

AB - Longitudinal studies of aging often gather repeated observations of cognitive status to describe the development of dementia and to assess the influence of risk factors. Clinical progression to dementia is often conceptualized by a multi-stage model of several transitions that synthesizes time-varying effects. In this study, we assess the influence of risk factors on the transitions among three cognitive status: cognitive stability (normal cognition for age), memory impairment, and clinical dementia. We have developed a shared random effects model that not only links the propensity of transitions and to the probability of informative missingness due to death, but also incorporates heterogeneous transition between subjects. We evaluate four approaches using generalized logit and four using proportional odds models to the first-order Markov transition probabilities as a function of covariates. Random effects were incorporated into these models to account for within-subject correlations. Data from the Einstein Aging Study are used to evaluate the goodness-of-fit of these models using the Akaike information criterion. The best fitting model for each type (generalized logit and proportional odds) is recommended and their results are discussed in more details.

KW - Generalized logit

KW - Multi-stage

KW - Proportional odds

KW - Random effects

KW - Transition

UR - http://www.scopus.com/inward/record.url?scp=80755143348&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80755143348&partnerID=8YFLogxK

U2 - 10.1002/bimj.200900259

DO - 10.1002/bimj.200900259

M3 - Article

C2 - 22020750

AN - SCOPUS:80755143348

VL - 53

SP - 938

EP - 955

JO - Biometrical Journal

JF - Biometrical Journal

SN - 0323-3847

IS - 6

ER -