Bayesian analysis of longitudinal data using growth curve models

Zhiyong Zhang, Fumiaki Hamagami, Lijuan Wang, John R. Nesselroade, Kevin Grimm

Research output: Contribution to journalArticle

72 Citations (Scopus)

Abstract

Bayesian methods for analyzing longitudinal data in social and behavioral research are recommended for their ability to incorporate prior information in estimating simple and complex models. We first summarize the basics of Bayesian methods before presenting an empirical example in which we fit a latent basis growth curve model to achievement data from the National Longitudinal Survey of Youth. This step-by-step example illustrates how to analyze data using both noninformative and informative priors. The results show that in addition to being an alternative to the maximum likelihood estimation (MLE) method, Bayesian methods also have unique strengths, such as the systematic incorporation of prior information from previous studies. These methods are more plausible ways to analyze small sample data compared with the MLE method.

Original languageEnglish (US)
Pages (from-to)374-383
Number of pages10
JournalInternational Journal of Behavioral Development
Volume31
Issue number4
DOIs
StatePublished - Jul 2007
Externally publishedYes

Fingerprint

Bayes Theorem
Growth
Behavioral Research
Aptitude
Longitudinal Studies
behavioral research
social research
ability

Keywords

  • Bayesian analysis
  • Growth curve models
  • Informative priors
  • Longitudinal data
  • Pooling data
  • WinBUGS

ASJC Scopus subject areas

  • Psychology(all)
  • Developmental and Educational Psychology

Cite this

Bayesian analysis of longitudinal data using growth curve models. / Zhang, Zhiyong; Hamagami, Fumiaki; Wang, Lijuan; Nesselroade, John R.; Grimm, Kevin.

In: International Journal of Behavioral Development, Vol. 31, No. 4, 07.2007, p. 374-383.

Research output: Contribution to journalArticle

Zhang, Zhiyong ; Hamagami, Fumiaki ; Wang, Lijuan ; Nesselroade, John R. ; Grimm, Kevin. / Bayesian analysis of longitudinal data using growth curve models. In: International Journal of Behavioral Development. 2007 ; Vol. 31, No. 4. pp. 374-383.
@article{dc78bb0ebb6c437bb8f5e5eaa1e86b47,
title = "Bayesian analysis of longitudinal data using growth curve models",
abstract = "Bayesian methods for analyzing longitudinal data in social and behavioral research are recommended for their ability to incorporate prior information in estimating simple and complex models. We first summarize the basics of Bayesian methods before presenting an empirical example in which we fit a latent basis growth curve model to achievement data from the National Longitudinal Survey of Youth. This step-by-step example illustrates how to analyze data using both noninformative and informative priors. The results show that in addition to being an alternative to the maximum likelihood estimation (MLE) method, Bayesian methods also have unique strengths, such as the systematic incorporation of prior information from previous studies. These methods are more plausible ways to analyze small sample data compared with the MLE method.",
keywords = "Bayesian analysis, Growth curve models, Informative priors, Longitudinal data, Pooling data, WinBUGS",
author = "Zhiyong Zhang and Fumiaki Hamagami and Lijuan Wang and Nesselroade, {John R.} and Kevin Grimm",
year = "2007",
month = "7",
doi = "10.1177/0165025407077764",
language = "English (US)",
volume = "31",
pages = "374--383",
journal = "International Journal of Behavioral Development",
issn = "0165-0254",
publisher = "SAGE Publications Ltd",
number = "4",

}

TY - JOUR

T1 - Bayesian analysis of longitudinal data using growth curve models

AU - Zhang, Zhiyong

AU - Hamagami, Fumiaki

AU - Wang, Lijuan

AU - Nesselroade, John R.

AU - Grimm, Kevin

PY - 2007/7

Y1 - 2007/7

N2 - Bayesian methods for analyzing longitudinal data in social and behavioral research are recommended for their ability to incorporate prior information in estimating simple and complex models. We first summarize the basics of Bayesian methods before presenting an empirical example in which we fit a latent basis growth curve model to achievement data from the National Longitudinal Survey of Youth. This step-by-step example illustrates how to analyze data using both noninformative and informative priors. The results show that in addition to being an alternative to the maximum likelihood estimation (MLE) method, Bayesian methods also have unique strengths, such as the systematic incorporation of prior information from previous studies. These methods are more plausible ways to analyze small sample data compared with the MLE method.

AB - Bayesian methods for analyzing longitudinal data in social and behavioral research are recommended for their ability to incorporate prior information in estimating simple and complex models. We first summarize the basics of Bayesian methods before presenting an empirical example in which we fit a latent basis growth curve model to achievement data from the National Longitudinal Survey of Youth. This step-by-step example illustrates how to analyze data using both noninformative and informative priors. The results show that in addition to being an alternative to the maximum likelihood estimation (MLE) method, Bayesian methods also have unique strengths, such as the systematic incorporation of prior information from previous studies. These methods are more plausible ways to analyze small sample data compared with the MLE method.

KW - Bayesian analysis

KW - Growth curve models

KW - Informative priors

KW - Longitudinal data

KW - Pooling data

KW - WinBUGS

UR - http://www.scopus.com/inward/record.url?scp=34347330128&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34347330128&partnerID=8YFLogxK

U2 - 10.1177/0165025407077764

DO - 10.1177/0165025407077764

M3 - Article

AN - SCOPUS:34347330128

VL - 31

SP - 374

EP - 383

JO - International Journal of Behavioral Development

JF - International Journal of Behavioral Development

SN - 0165-0254

IS - 4

ER -