Correcting Model Fit Criteria for Small Sample Latent Growth Models With Incomplete Data

Daniel McNeish, Jeffrey R. Harring

Research output: Contribution to journalArticle

7 Citations (Scopus)

Abstract

To date, small sample problems with latent growth models (LGMs) have not received the amount of attention in the literature as related mixed-effect models (MEMs). Although many models can be interchangeably framed as a LGM or a MEM, LGMs uniquely provide criteria to assess global data–model fit. However, previous studies have demonstrated poor small sample performance of these global data–model fit criteria and three post hoc small sample corrections have been proposed and shown to perform well with complete data. However, these corrections use sample size in their computation—whose value is unclear when missing data are accommodated with full information maximum likelihood, as is common with LGMs. A simulation is provided to demonstrate the inadequacy of these small sample corrections in the near ubiquitous situation in growth modeling where data are incomplete. Then, a missing data correction for the small sample correction equations is proposed and shown through a simulation study to perform well in various conditions found in practice. An applied developmental psychology example is then provided to demonstrate how disregarding missing data in small sample correction equations can greatly affect assessment of global data–model fit.

Original languageEnglish (US)
Pages (from-to)990-1018
Number of pages29
JournalEducational and Psychological Measurement
Volume77
Issue number6
DOIs
StatePublished - Dec 1 2017
Externally publishedYes

Fingerprint

Incomplete Data
Growth Model
Small Sample
Growth
Missing Data
Mixed Effects Model
Applied Psychology
Model
Sample Size
developmental psychology
simulation
Demonstrate
Maximum Likelihood
Maximum likelihood
Data structures
Simulation Study
Modeling
Simulation
performance
Values

Keywords

  • correction
  • dropout
  • FIML
  • full information maximum likelihood
  • latent growth model
  • missing data
  • small sample

ASJC Scopus subject areas

  • Education
  • Developmental and Educational Psychology
  • Applied Psychology
  • Applied Mathematics

Cite this

Correcting Model Fit Criteria for Small Sample Latent Growth Models With Incomplete Data. / McNeish, Daniel; Harring, Jeffrey R.

In: Educational and Psychological Measurement, Vol. 77, No. 6, 01.12.2017, p. 990-1018.

Research output: Contribution to journalArticle

@article{8abce326d3ed4699b4d6446773d813fb,
title = "Correcting Model Fit Criteria for Small Sample Latent Growth Models With Incomplete Data",
abstract = "To date, small sample problems with latent growth models (LGMs) have not received the amount of attention in the literature as related mixed-effect models (MEMs). Although many models can be interchangeably framed as a LGM or a MEM, LGMs uniquely provide criteria to assess global data–model fit. However, previous studies have demonstrated poor small sample performance of these global data–model fit criteria and three post hoc small sample corrections have been proposed and shown to perform well with complete data. However, these corrections use sample size in their computation—whose value is unclear when missing data are accommodated with full information maximum likelihood, as is common with LGMs. A simulation is provided to demonstrate the inadequacy of these small sample corrections in the near ubiquitous situation in growth modeling where data are incomplete. Then, a missing data correction for the small sample correction equations is proposed and shown through a simulation study to perform well in various conditions found in practice. An applied developmental psychology example is then provided to demonstrate how disregarding missing data in small sample correction equations can greatly affect assessment of global data–model fit.",
keywords = "correction, dropout, FIML, full information maximum likelihood, latent growth model, missing data, small sample",
author = "Daniel McNeish and Harring, {Jeffrey R.}",
year = "2017",
month = "12",
day = "1",
doi = "10.1177/0013164416661824",
language = "English (US)",
volume = "77",
pages = "990--1018",
journal = "Educational and Psychological Measurement",
issn = "0013-1644",
publisher = "SAGE Publications Inc.",
number = "6",

}

TY - JOUR

T1 - Correcting Model Fit Criteria for Small Sample Latent Growth Models With Incomplete Data

AU - McNeish, Daniel

AU - Harring, Jeffrey R.

PY - 2017/12/1

Y1 - 2017/12/1

N2 - To date, small sample problems with latent growth models (LGMs) have not received the amount of attention in the literature as related mixed-effect models (MEMs). Although many models can be interchangeably framed as a LGM or a MEM, LGMs uniquely provide criteria to assess global data–model fit. However, previous studies have demonstrated poor small sample performance of these global data–model fit criteria and three post hoc small sample corrections have been proposed and shown to perform well with complete data. However, these corrections use sample size in their computation—whose value is unclear when missing data are accommodated with full information maximum likelihood, as is common with LGMs. A simulation is provided to demonstrate the inadequacy of these small sample corrections in the near ubiquitous situation in growth modeling where data are incomplete. Then, a missing data correction for the small sample correction equations is proposed and shown through a simulation study to perform well in various conditions found in practice. An applied developmental psychology example is then provided to demonstrate how disregarding missing data in small sample correction equations can greatly affect assessment of global data–model fit.

AB - To date, small sample problems with latent growth models (LGMs) have not received the amount of attention in the literature as related mixed-effect models (MEMs). Although many models can be interchangeably framed as a LGM or a MEM, LGMs uniquely provide criteria to assess global data–model fit. However, previous studies have demonstrated poor small sample performance of these global data–model fit criteria and three post hoc small sample corrections have been proposed and shown to perform well with complete data. However, these corrections use sample size in their computation—whose value is unclear when missing data are accommodated with full information maximum likelihood, as is common with LGMs. A simulation is provided to demonstrate the inadequacy of these small sample corrections in the near ubiquitous situation in growth modeling where data are incomplete. Then, a missing data correction for the small sample correction equations is proposed and shown through a simulation study to perform well in various conditions found in practice. An applied developmental psychology example is then provided to demonstrate how disregarding missing data in small sample correction equations can greatly affect assessment of global data–model fit.

KW - correction

KW - dropout

KW - FIML

KW - full information maximum likelihood

KW - latent growth model

KW - missing data

KW - small sample

UR - http://www.scopus.com/inward/record.url?scp=85032741085&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85032741085&partnerID=8YFLogxK

U2 - 10.1177/0013164416661824

DO - 10.1177/0013164416661824

M3 - Article

AN - SCOPUS:85032741085

VL - 77

SP - 990

EP - 1018

JO - Educational and Psychological Measurement

JF - Educational and Psychological Measurement

SN - 0013-1644

IS - 6

ER -