Latent growth modeling of IRT versus CTT measured longitudinal latent variables

R. Gorter*, J. P. Fox, G. Ter Riet, M. W. Heymans, J. W.R. Twisk

*Corresponding author for this work

Research output: Contribution to journalArticleAcademicpeer-review

Abstract

Latent growth models are often used to measure individual trajectories representing change over time. The characteristics of the individual trajectories depend on the variability in the longitudinal outcomes. In many medical and epidemiological studies, the individual health outcomes cannot be observed directly and are indirectly observed through indicators (i.e. items of a questionnaire). An item response theory or a classical test theory measurement model is required, but the choice can influence the latent growth estimates. In this study, under various conditions, this influence is directly assessed by estimating latent growth parameters on a common scale for item response theory and classical test theory using a novel plausible value method in combination with Markov chain Monte Carlo. The latent outcomes are considered missing data and plausible values are generated from the corresponding posterior distribution, separately for item response theory and classical test theory. These plausible values are linearly transformed to a common scale. A Markov chain Monte Carlo method was developed to simultaneously estimate the latent growth and measurement model parameters using this plausible value technique. It is shown that estimated individual trajectories using item response theory, compared to classical test theory to measure outcomes, provide a more detailed description of individual change over time, since item response patterns (item response theory) are more informative about the health measurements than sum scores (classical test theory).

Original languageEnglish
JournalStatistical methods in medical research
DOIs
Publication statusE-pub ahead of print/First online - 4 Jul 2019

Fingerprint

Test Theory
Latent Variables
Markov Chains
Growth
Modeling
Trajectory
Monte Carlo Method
Health
Epidemiologic Studies
Markov Chain Monte Carlo Methods
Outcome Assessment (Health Care)
Growth Model
Markov Chain Monte Carlo
Posterior distribution
Missing Data
Questionnaire
Estimate
Linearly
Model

Keywords

  • UT-Hybrid-D
  • latent growth model
  • Longitudinal data
  • multilevel item response theory
  • multiple imputation
  • questionnaires
  • classical test theory

Cite this

@article{32c58053047b479481b45e80c80691b4,
title = "Latent growth modeling of IRT versus CTT measured longitudinal latent variables",
abstract = "Latent growth models are often used to measure individual trajectories representing change over time. The characteristics of the individual trajectories depend on the variability in the longitudinal outcomes. In many medical and epidemiological studies, the individual health outcomes cannot be observed directly and are indirectly observed through indicators (i.e. items of a questionnaire). An item response theory or a classical test theory measurement model is required, but the choice can influence the latent growth estimates. In this study, under various conditions, this influence is directly assessed by estimating latent growth parameters on a common scale for item response theory and classical test theory using a novel plausible value method in combination with Markov chain Monte Carlo. The latent outcomes are considered missing data and plausible values are generated from the corresponding posterior distribution, separately for item response theory and classical test theory. These plausible values are linearly transformed to a common scale. A Markov chain Monte Carlo method was developed to simultaneously estimate the latent growth and measurement model parameters using this plausible value technique. It is shown that estimated individual trajectories using item response theory, compared to classical test theory to measure outcomes, provide a more detailed description of individual change over time, since item response patterns (item response theory) are more informative about the health measurements than sum scores (classical test theory).",
keywords = "UT-Hybrid-D, latent growth model, Longitudinal data, multilevel item response theory, multiple imputation, questionnaires, classical test theory",
author = "R. Gorter and Fox, {J. P.} and Riet, {G. Ter} and Heymans, {M. W.} and Twisk, {J. W.R.}",
note = "Sage deal",
year = "2019",
month = "7",
day = "4",
doi = "10.1177/0962280219856375",
language = "English",
journal = "Statistical methods in medical research",
issn = "0962-2802",
publisher = "SAGE Publications",

}

Latent growth modeling of IRT versus CTT measured longitudinal latent variables. / Gorter, R.; Fox, J. P.; Riet, G. Ter; Heymans, M. W.; Twisk, J. W.R.

In: Statistical methods in medical research, 04.07.2019.

Research output: Contribution to journalArticleAcademicpeer-review

TY - JOUR

T1 - Latent growth modeling of IRT versus CTT measured longitudinal latent variables

AU - Gorter, R.

AU - Fox, J. P.

AU - Riet, G. Ter

AU - Heymans, M. W.

AU - Twisk, J. W.R.

N1 - Sage deal

PY - 2019/7/4

Y1 - 2019/7/4

N2 - Latent growth models are often used to measure individual trajectories representing change over time. The characteristics of the individual trajectories depend on the variability in the longitudinal outcomes. In many medical and epidemiological studies, the individual health outcomes cannot be observed directly and are indirectly observed through indicators (i.e. items of a questionnaire). An item response theory or a classical test theory measurement model is required, but the choice can influence the latent growth estimates. In this study, under various conditions, this influence is directly assessed by estimating latent growth parameters on a common scale for item response theory and classical test theory using a novel plausible value method in combination with Markov chain Monte Carlo. The latent outcomes are considered missing data and plausible values are generated from the corresponding posterior distribution, separately for item response theory and classical test theory. These plausible values are linearly transformed to a common scale. A Markov chain Monte Carlo method was developed to simultaneously estimate the latent growth and measurement model parameters using this plausible value technique. It is shown that estimated individual trajectories using item response theory, compared to classical test theory to measure outcomes, provide a more detailed description of individual change over time, since item response patterns (item response theory) are more informative about the health measurements than sum scores (classical test theory).

AB - Latent growth models are often used to measure individual trajectories representing change over time. The characteristics of the individual trajectories depend on the variability in the longitudinal outcomes. In many medical and epidemiological studies, the individual health outcomes cannot be observed directly and are indirectly observed through indicators (i.e. items of a questionnaire). An item response theory or a classical test theory measurement model is required, but the choice can influence the latent growth estimates. In this study, under various conditions, this influence is directly assessed by estimating latent growth parameters on a common scale for item response theory and classical test theory using a novel plausible value method in combination with Markov chain Monte Carlo. The latent outcomes are considered missing data and plausible values are generated from the corresponding posterior distribution, separately for item response theory and classical test theory. These plausible values are linearly transformed to a common scale. A Markov chain Monte Carlo method was developed to simultaneously estimate the latent growth and measurement model parameters using this plausible value technique. It is shown that estimated individual trajectories using item response theory, compared to classical test theory to measure outcomes, provide a more detailed description of individual change over time, since item response patterns (item response theory) are more informative about the health measurements than sum scores (classical test theory).

KW - UT-Hybrid-D

KW - latent growth model

KW - Longitudinal data

KW - multilevel item response theory

KW - multiple imputation

KW - questionnaires

KW - classical test theory

UR - http://www.scopus.com/inward/record.url?scp=85068590626&partnerID=8YFLogxK

U2 - 10.1177/0962280219856375

DO - 10.1177/0962280219856375

M3 - Article

AN - SCOPUS:85068590626

JO - Statistical methods in medical research

JF - Statistical methods in medical research

SN - 0962-2802

ER -