A note on estimating single-class piecewise mixed-effects models with unknown change points

Nidhi Kohli, Yadira Peralta, Cengiz Zopluoglu, Mark L Davison

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Piecewise mixed-effects models are useful for analyzing longitudinal educational and psychological data sets to model segmented change over time. These models offer an attractive alternative to commonly used quadratic and higher-order polynomial models because the coefficients obtained from fitting the model have meaningful substantive interpretation. The current study thus focuses on the estimation of piecewise mixed-effects model with unknown random change points using maximum likelihood (ML) as described in Du Toit and Cudeck (2009). Previous simulation work (Wang & McArdle, 2008) showed that Bayesian estimation produced reliable parameter estimates for the piecewise model in comparison to frequentist procedures (i.e., first-order Taylor expansion and the adaptive Gaussian quadrature) across all simulation conditions. In the current article a small Monte Carlo simulation study was conducted to assess the performance of the ML approach, a frequentist procedure, and the Bayesian approach for fitting linear–linear piecewise mixed-effects model. The obtained findings show that ML estimation approach produces reliable and accurate estimates under the conditions of small residual variance of the observed variables, and that the size of the residual variance had the most impact on the quality of model parameter estimates. Second, neither ML nor Bayesian estimation procedures performed well under all manipulated conditions with respect to the accuracy and precision of the estimated model parameters.

Original languageEnglish (US)
Pages (from-to)518-524
Number of pages7
JournalInternational Journal of Behavioral Development
Volume42
Issue number5
DOIs
StatePublished - Sep 1 2018

Fingerprint

Bayes Theorem
Statistical Models
Psychology
simulation
estimation procedure
interpretation
Datasets
performance

Keywords

  • Longitudinal data set
  • change points
  • maximum likelihood
  • piecewise function

Cite this

A note on estimating single-class piecewise mixed-effects models with unknown change points. / Kohli, Nidhi; Peralta, Yadira; Zopluoglu, Cengiz; Davison, Mark L.

In: International Journal of Behavioral Development, Vol. 42, No. 5, 01.09.2018, p. 518-524.

Research output: Contribution to journalArticle

@article{bcbaa02398cf456682fb21e8165761dd,
title = "A note on estimating single-class piecewise mixed-effects models with unknown change points",
abstract = "Piecewise mixed-effects models are useful for analyzing longitudinal educational and psychological data sets to model segmented change over time. These models offer an attractive alternative to commonly used quadratic and higher-order polynomial models because the coefficients obtained from fitting the model have meaningful substantive interpretation. The current study thus focuses on the estimation of piecewise mixed-effects model with unknown random change points using maximum likelihood (ML) as described in Du Toit and Cudeck (2009). Previous simulation work (Wang & McArdle, 2008) showed that Bayesian estimation produced reliable parameter estimates for the piecewise model in comparison to frequentist procedures (i.e., first-order Taylor expansion and the adaptive Gaussian quadrature) across all simulation conditions. In the current article a small Monte Carlo simulation study was conducted to assess the performance of the ML approach, a frequentist procedure, and the Bayesian approach for fitting linear–linear piecewise mixed-effects model. The obtained findings show that ML estimation approach produces reliable and accurate estimates under the conditions of small residual variance of the observed variables, and that the size of the residual variance had the most impact on the quality of model parameter estimates. Second, neither ML nor Bayesian estimation procedures performed well under all manipulated conditions with respect to the accuracy and precision of the estimated model parameters.",
keywords = "Longitudinal data set, change points, maximum likelihood, piecewise function",
author = "Nidhi Kohli and Yadira Peralta and Cengiz Zopluoglu and Davison, {Mark L}",
year = "2018",
month = "9",
day = "1",
doi = "10.1177/0165025418759237",
language = "English (US)",
volume = "42",
pages = "518--524",
journal = "International Journal of Behavioral Development",
issn = "0165-0254",
publisher = "SAGE Publications Ltd",
number = "5",

}

TY - JOUR

T1 - A note on estimating single-class piecewise mixed-effects models with unknown change points

AU - Kohli, Nidhi

AU - Peralta, Yadira

AU - Zopluoglu, Cengiz

AU - Davison, Mark L

PY - 2018/9/1

Y1 - 2018/9/1

N2 - Piecewise mixed-effects models are useful for analyzing longitudinal educational and psychological data sets to model segmented change over time. These models offer an attractive alternative to commonly used quadratic and higher-order polynomial models because the coefficients obtained from fitting the model have meaningful substantive interpretation. The current study thus focuses on the estimation of piecewise mixed-effects model with unknown random change points using maximum likelihood (ML) as described in Du Toit and Cudeck (2009). Previous simulation work (Wang & McArdle, 2008) showed that Bayesian estimation produced reliable parameter estimates for the piecewise model in comparison to frequentist procedures (i.e., first-order Taylor expansion and the adaptive Gaussian quadrature) across all simulation conditions. In the current article a small Monte Carlo simulation study was conducted to assess the performance of the ML approach, a frequentist procedure, and the Bayesian approach for fitting linear–linear piecewise mixed-effects model. The obtained findings show that ML estimation approach produces reliable and accurate estimates under the conditions of small residual variance of the observed variables, and that the size of the residual variance had the most impact on the quality of model parameter estimates. Second, neither ML nor Bayesian estimation procedures performed well under all manipulated conditions with respect to the accuracy and precision of the estimated model parameters.

AB - Piecewise mixed-effects models are useful for analyzing longitudinal educational and psychological data sets to model segmented change over time. These models offer an attractive alternative to commonly used quadratic and higher-order polynomial models because the coefficients obtained from fitting the model have meaningful substantive interpretation. The current study thus focuses on the estimation of piecewise mixed-effects model with unknown random change points using maximum likelihood (ML) as described in Du Toit and Cudeck (2009). Previous simulation work (Wang & McArdle, 2008) showed that Bayesian estimation produced reliable parameter estimates for the piecewise model in comparison to frequentist procedures (i.e., first-order Taylor expansion and the adaptive Gaussian quadrature) across all simulation conditions. In the current article a small Monte Carlo simulation study was conducted to assess the performance of the ML approach, a frequentist procedure, and the Bayesian approach for fitting linear–linear piecewise mixed-effects model. The obtained findings show that ML estimation approach produces reliable and accurate estimates under the conditions of small residual variance of the observed variables, and that the size of the residual variance had the most impact on the quality of model parameter estimates. Second, neither ML nor Bayesian estimation procedures performed well under all manipulated conditions with respect to the accuracy and precision of the estimated model parameters.

KW - Longitudinal data set

KW - change points

KW - maximum likelihood

KW - piecewise function

UR - http://www.scopus.com/inward/record.url?scp=85042105479&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85042105479&partnerID=8YFLogxK

U2 - 10.1177/0165025418759237

DO - 10.1177/0165025418759237

M3 - Article

VL - 42

SP - 518

EP - 524

JO - International Journal of Behavioral Development

JF - International Journal of Behavioral Development

SN - 0165-0254

IS - 5

ER -