Latent growth models matched to research questions to answer questions about dynamics of change in multiple processes

Graciela Muniz-Terrera, Annie Robitaille, Amanda Kelly, Boo Johansson, Scott Hofer, Andrea Piccinin

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

Objectives Given theoretical and methodological advances that propose hypothesis about change in one or multiple processes, analytical methods for longitudinal data have been developed that provide researchers with various options for analyzing change over time. In this paper, we revisited several latent growth curve models that may be considered to answer questions about repeated measures of continuous variables, which may be operationalized as time-varying covariates or outcomes. Study Design and Setting To illustrate each of the models discussed and how to interpret parameter estimates, we present examples of each method discussed using cognitive and blood pressure measures from a longitudinal study of aging, the Origins of Variance in the Old-Old study. Results and Conclusion Although statistical models are helpful tools to test theoretical hypotheses about the dynamics between multiple processes, the choice of model and its specification will influence results and conclusions made.

Original languageEnglish (US)
Pages (from-to)158-166
Number of pages9
JournalJournal of Clinical Epidemiology
Volume82
DOIs
StatePublished - Feb 1 2017
Externally publishedYes

Fingerprint

Statistical Models
Growth
Research
Longitudinal Studies
Research Personnel
Blood Pressure

Keywords

  • Bivariate latent growth model
  • Latent growth model
  • Longitudinal models
  • Repeated measures, Multilevel models
  • Time-varying covariates

ASJC Scopus subject areas

  • Epidemiology

Cite this

Latent growth models matched to research questions to answer questions about dynamics of change in multiple processes. / Muniz-Terrera, Graciela; Robitaille, Annie; Kelly, Amanda; Johansson, Boo; Hofer, Scott; Piccinin, Andrea.

In: Journal of Clinical Epidemiology, Vol. 82, 01.02.2017, p. 158-166.

Research output: Contribution to journalArticle

Muniz-Terrera, Graciela ; Robitaille, Annie ; Kelly, Amanda ; Johansson, Boo ; Hofer, Scott ; Piccinin, Andrea. / Latent growth models matched to research questions to answer questions about dynamics of change in multiple processes. In: Journal of Clinical Epidemiology. 2017 ; Vol. 82. pp. 158-166.
@article{96771b8d8a244adb9aad14dd5e2ddda6,
title = "Latent growth models matched to research questions to answer questions about dynamics of change in multiple processes",
abstract = "Objectives Given theoretical and methodological advances that propose hypothesis about change in one or multiple processes, analytical methods for longitudinal data have been developed that provide researchers with various options for analyzing change over time. In this paper, we revisited several latent growth curve models that may be considered to answer questions about repeated measures of continuous variables, which may be operationalized as time-varying covariates or outcomes. Study Design and Setting To illustrate each of the models discussed and how to interpret parameter estimates, we present examples of each method discussed using cognitive and blood pressure measures from a longitudinal study of aging, the Origins of Variance in the Old-Old study. Results and Conclusion Although statistical models are helpful tools to test theoretical hypotheses about the dynamics between multiple processes, the choice of model and its specification will influence results and conclusions made.",
keywords = "Bivariate latent growth model, Latent growth model, Longitudinal models, Repeated measures, Multilevel models, Time-varying covariates",
author = "Graciela Muniz-Terrera and Annie Robitaille and Amanda Kelly and Boo Johansson and Scott Hofer and Andrea Piccinin",
year = "2017",
month = "2",
day = "1",
doi = "10.1016/j.jclinepi.2016.09.001",
language = "English (US)",
volume = "82",
pages = "158--166",
journal = "Journal of Clinical Epidemiology",
issn = "0895-4356",
publisher = "Elsevier USA",

}

TY - JOUR

T1 - Latent growth models matched to research questions to answer questions about dynamics of change in multiple processes

AU - Muniz-Terrera, Graciela

AU - Robitaille, Annie

AU - Kelly, Amanda

AU - Johansson, Boo

AU - Hofer, Scott

AU - Piccinin, Andrea

PY - 2017/2/1

Y1 - 2017/2/1

N2 - Objectives Given theoretical and methodological advances that propose hypothesis about change in one or multiple processes, analytical methods for longitudinal data have been developed that provide researchers with various options for analyzing change over time. In this paper, we revisited several latent growth curve models that may be considered to answer questions about repeated measures of continuous variables, which may be operationalized as time-varying covariates or outcomes. Study Design and Setting To illustrate each of the models discussed and how to interpret parameter estimates, we present examples of each method discussed using cognitive and blood pressure measures from a longitudinal study of aging, the Origins of Variance in the Old-Old study. Results and Conclusion Although statistical models are helpful tools to test theoretical hypotheses about the dynamics between multiple processes, the choice of model and its specification will influence results and conclusions made.

AB - Objectives Given theoretical and methodological advances that propose hypothesis about change in one or multiple processes, analytical methods for longitudinal data have been developed that provide researchers with various options for analyzing change over time. In this paper, we revisited several latent growth curve models that may be considered to answer questions about repeated measures of continuous variables, which may be operationalized as time-varying covariates or outcomes. Study Design and Setting To illustrate each of the models discussed and how to interpret parameter estimates, we present examples of each method discussed using cognitive and blood pressure measures from a longitudinal study of aging, the Origins of Variance in the Old-Old study. Results and Conclusion Although statistical models are helpful tools to test theoretical hypotheses about the dynamics between multiple processes, the choice of model and its specification will influence results and conclusions made.

KW - Bivariate latent growth model

KW - Latent growth model

KW - Longitudinal models

KW - Repeated measures, Multilevel models

KW - Time-varying covariates

UR - http://www.scopus.com/inward/record.url?scp=85006035897&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85006035897&partnerID=8YFLogxK

U2 - 10.1016/j.jclinepi.2016.09.001

DO - 10.1016/j.jclinepi.2016.09.001

M3 - Article

C2 - 27639542

AN - SCOPUS:85006035897

VL - 82

SP - 158

EP - 166

JO - Journal of Clinical Epidemiology

JF - Journal of Clinical Epidemiology

SN - 0895-4356

ER -