Testing Measurement Invariance in Longitudinal Data With Ordered-Categorical Measures

Yu Liu, Roger E. Millsap, Stephen West, Jenn-Yun Tein, Rika Tanaka, Kevin Grimm

Research output: Contribution to journalArticle

24 Citations (Scopus)

Abstract

A goal of developmental research is to examine individual changes in constructs over time. The accuracy of the models answering such research questions hinges on the assumption of longitudinal measurement invariance: The repeatedly measured variables need to represent the same construct in the same metric over time. Measurement invariance can be studied through factor models examining the relations between the observed indicators and the latent constructs. In longitudinal research, ordered-categorical indicators such as self- or observer-report Likert scales are commonly used, and these measures often do not approximate continuous normal distributions. The present didactic article extends previous work on measurement invariance to the longitudinal case for ordered-categorical indicators. We address a number of problems that commonly arise in testing measurement invariance with longitudinal data, including model identification and interpretation, sparse data, missing data, and estimation issues. We also develop a procedure and associated R program for gauging the practical significance of the violations of invariance. We illustrate these issues with an empirical example using a subscale from the Mexican American Cultural Values scale. Finally, we provide comparisons of the current capabilities of 3 major latent variable programs (lavaan, Mplus, OpenMx) and computer scripts for addressing longitudinal measurement invariance. (PsycINFO Database Record

Original languageEnglish (US)
JournalPsychological Methods
DOIs
StateAccepted/In press - May 23 2016

Fingerprint

Research
Normal Distribution

Keywords

  • Confirmatory factor analysis
  • Longitudinal
  • Measurement invariance
  • Ordered-categorical
  • Practical significance

ASJC Scopus subject areas

  • Psychology (miscellaneous)

Cite this

Testing Measurement Invariance in Longitudinal Data With Ordered-Categorical Measures. / Liu, Yu; Millsap, Roger E.; West, Stephen; Tein, Jenn-Yun; Tanaka, Rika; Grimm, Kevin.

In: Psychological Methods, 23.05.2016.

Research output: Contribution to journalArticle

@article{fdda4b250587498f8f4775b246af05c6,
title = "Testing Measurement Invariance in Longitudinal Data With Ordered-Categorical Measures",
abstract = "A goal of developmental research is to examine individual changes in constructs over time. The accuracy of the models answering such research questions hinges on the assumption of longitudinal measurement invariance: The repeatedly measured variables need to represent the same construct in the same metric over time. Measurement invariance can be studied through factor models examining the relations between the observed indicators and the latent constructs. In longitudinal research, ordered-categorical indicators such as self- or observer-report Likert scales are commonly used, and these measures often do not approximate continuous normal distributions. The present didactic article extends previous work on measurement invariance to the longitudinal case for ordered-categorical indicators. We address a number of problems that commonly arise in testing measurement invariance with longitudinal data, including model identification and interpretation, sparse data, missing data, and estimation issues. We also develop a procedure and associated R program for gauging the practical significance of the violations of invariance. We illustrate these issues with an empirical example using a subscale from the Mexican American Cultural Values scale. Finally, we provide comparisons of the current capabilities of 3 major latent variable programs (lavaan, Mplus, OpenMx) and computer scripts for addressing longitudinal measurement invariance. (PsycINFO Database Record",
keywords = "Confirmatory factor analysis, Longitudinal, Measurement invariance, Ordered-categorical, Practical significance",
author = "Yu Liu and Millsap, {Roger E.} and Stephen West and Jenn-Yun Tein and Rika Tanaka and Kevin Grimm",
year = "2016",
month = "5",
day = "23",
doi = "10.1037/met0000075",
language = "English (US)",
journal = "Psychological Methods",
issn = "1082-989X",
publisher = "American Psychological Association Inc.",

}

TY - JOUR

T1 - Testing Measurement Invariance in Longitudinal Data With Ordered-Categorical Measures

AU - Liu, Yu

AU - Millsap, Roger E.

AU - West, Stephen

AU - Tein, Jenn-Yun

AU - Tanaka, Rika

AU - Grimm, Kevin

PY - 2016/5/23

Y1 - 2016/5/23

N2 - A goal of developmental research is to examine individual changes in constructs over time. The accuracy of the models answering such research questions hinges on the assumption of longitudinal measurement invariance: The repeatedly measured variables need to represent the same construct in the same metric over time. Measurement invariance can be studied through factor models examining the relations between the observed indicators and the latent constructs. In longitudinal research, ordered-categorical indicators such as self- or observer-report Likert scales are commonly used, and these measures often do not approximate continuous normal distributions. The present didactic article extends previous work on measurement invariance to the longitudinal case for ordered-categorical indicators. We address a number of problems that commonly arise in testing measurement invariance with longitudinal data, including model identification and interpretation, sparse data, missing data, and estimation issues. We also develop a procedure and associated R program for gauging the practical significance of the violations of invariance. We illustrate these issues with an empirical example using a subscale from the Mexican American Cultural Values scale. Finally, we provide comparisons of the current capabilities of 3 major latent variable programs (lavaan, Mplus, OpenMx) and computer scripts for addressing longitudinal measurement invariance. (PsycINFO Database Record

AB - A goal of developmental research is to examine individual changes in constructs over time. The accuracy of the models answering such research questions hinges on the assumption of longitudinal measurement invariance: The repeatedly measured variables need to represent the same construct in the same metric over time. Measurement invariance can be studied through factor models examining the relations between the observed indicators and the latent constructs. In longitudinal research, ordered-categorical indicators such as self- or observer-report Likert scales are commonly used, and these measures often do not approximate continuous normal distributions. The present didactic article extends previous work on measurement invariance to the longitudinal case for ordered-categorical indicators. We address a number of problems that commonly arise in testing measurement invariance with longitudinal data, including model identification and interpretation, sparse data, missing data, and estimation issues. We also develop a procedure and associated R program for gauging the practical significance of the violations of invariance. We illustrate these issues with an empirical example using a subscale from the Mexican American Cultural Values scale. Finally, we provide comparisons of the current capabilities of 3 major latent variable programs (lavaan, Mplus, OpenMx) and computer scripts for addressing longitudinal measurement invariance. (PsycINFO Database Record

KW - Confirmatory factor analysis

KW - Longitudinal

KW - Measurement invariance

KW - Ordered-categorical

KW - Practical significance

UR - http://www.scopus.com/inward/record.url?scp=84969194846&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84969194846&partnerID=8YFLogxK

U2 - 10.1037/met0000075

DO - 10.1037/met0000075

M3 - Article

JO - Psychological Methods

JF - Psychological Methods

SN - 1082-989X

ER -