Testing Measurement Invariance Across Groups in Longitudinal Data: Multigroup Second-Order Latent Growth Model

Kim, Eun Sook; Willson, Victor L.

doi:10.1080/10705511.2014.919821

Cited by 25 publications

(19 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Additional details on technical specifications of these LGM models are provided in the online supplements. In order to assess whether the growth function generalized across groups of adolescents (Kim & Wilson, 2014a, 2014b, equality constraints were progressively integrated across groups on the: (i) mean of the growth factors reflecting the average growth trajectories in each group; (ii) variance of the growth factors, reflecting inter-individual deviations around the mean growth trajectories in each group; (iii) covariance of the growth factors, reflecting the degree to which the growth factors are inter-related within each group; (iv) time-specific residuals reflecting inter-individual deviations from the model-estimated quadratic trajectories. Predictors were then incorporated and allowed influence the growth factors separately in both groups.…”

Section: Methods Sample Procedures and Matchingmentioning

confidence: 99%

Self-Esteem Trajectories and Their Social Determinants in Adolescents With Different Levels of Cognitive Ability

Morin

Arens

Tracey

et al. 2017

American Journal on Intellectual and Developmental Disabilities

View full text Add to dashboard Cite

This study examines the development of self-esteem in a sample of 138 Australian adolescents (90 males; 48 females) with cognitive abilities in the lowest 15% (L-CA) and a matched sample of 556 Australian adolescents (312 males; 244 females) with average to high levels of cognitive abilities (A/H-CA). These participants were measured annually (Grade 7 to 12). The findings showed that adolescents with L-CA and A/H-CA experience similar high and stable self-esteem trajectories that present similar relations with key predictors (sex, school usefulness and dislike, parenting, and peer integration). Both groups revealed substantial gender differences showing higher levels of self-esteem for adolescent males remaining relatively stable over time, compared to lower levels among adolescent females which decreased until midadolescence before increasing back.

show abstract

Section: Methods Sample Procedures and Matchingmentioning

confidence: 99%

Self-Esteem Trajectories and Their Social Determinants in Adolescents With Different Levels of Cognitive Ability

Morin

Arens

Tracey

et al. 2017

American Journal on Intellectual and Developmental Disabilities

View full text Add to dashboard Cite

show abstract

“…Because configural ME/I is assessed by testing the absolute fit of the configural model, 2 for a multigroup model further confounds two sources of approximation discrepancy; the overall lack of correspondence between the population and analysis models could theoretically be partitioned into (a) differences among the groups' true population models and (b) discrepancies between each group's population and analysis models. It is possible (perhaps 1 Although "item" typically refers to a discretely measured test item, DIF has also been used to refer to measurement-parameter differences in the context of continuous indicators in CFA (e.g., Gonzalez-Roma, Tomas, Ferreres, & Hernandez, 2005;Kim & Willson, 2014), and Kline (2011, p. 253) referred to differentially functioning "indicators." Other terms have been used for the same phenomenon, such as measurement bias (Jak, Oort, & Dolan, 2010;Millsap, 2011, p. 47).…”

Section: Limitations Of Current Best Practicesmentioning

confidence: 99%

Permutation randomization methods for testing measurement equivalence and detecting differential item functioning in multiple-group confirmatory factor analysis.

Jorgensen

Kite

Chen

et al. 2018

Psychological Methods

View full text Add to dashboard Cite

In multigroup factor analysis, different levels of measurement invariance are accepted as tenable when researchers observe a nonsignificant (Δ)χ2 test after imposing certain equality constraints across groups. Large samples yield high power to detect negligible misspecifications, so many researchers prefer alternative fit indices (AFIs). Fixed cutoffs have been proposed for evaluating the effect of invariance constraints on change in AFIs (e.g., Chen, 2007; Cheung & Rensvold, 2002; Meade, Johnson, & Braddy, 2008). We demonstrate that all of these cutoffs have inconsistent Type I error rates. As a solution, we propose replacing χ2 and fixed AFI cutoffs with permutation tests. Randomly permuting group assignment results in average between-groups differences of zero, so iterative permutation yields an empirical distribution of any fit measure under the null hypothesis of invariance across groups. Our simulations show that the permutation test of configural invariance controls Type I error rates better than χ2 or AFIs when the model contains parsimony error (i.e., negligible misspecification) but the factor structure is equivalent across groups (i.e., the null hypothesis is true). For testing metric and scalar invariance, Δχ2 and permutation yield similar power and nominal Type I error rates, whereas ΔAFIs yield inflated errors in smaller samples. Permuting the maximum modification index among equality constraints control familywise Type I error rates when testing multiple indicators for lack of invariance, but provide similar power as using a Bonferroni adjustment. An applied example and syntax for software are provided. (PsycINFO Database Record (c) 2018 APA, all rights reserved).

show abstract

“…Likelihood ratio tests comparing these nested models were used to gauge the significance of the added restrictions in each successive model [ 56 ]. However, this mode of evaluation is confounded by sample size [ 57 ]; it does not separately identify features or gauge the magnitude of misconfiguration.…”

Section: Methodsmentioning

confidence: 99%

Comparison of factor analysis models applied to the NCANDA neuropsychological test battery

et al. 2022

View full text Add to dashboard Cite

The factor structure of neuropsychological functioning among a large sample (N = 831) of American youth (ages 12–21 at baseline) was investigated in order to identify an optimal model. Candidate models were selected based on their potential to provide service to the study of adolescent development and the effects of heavy episodic alcohol consumption. Data on neuropsychological functioning were obtained from the NCANDA study. This is a longitudinal community study of the effects of alcohol exposure on neurodevelopment. Three conceptually motivated and one empirically motivated factor analysis model of neuropsychological domains were compared based on penalized-likelihood selection criteria and model fit statistics. Two conceptually-motivated models were found to have adequate fit and pattern invariance to function as a measurement model for the Penn Computerized Neurocognitive Battery (Penn CNB) anchored neuropsychological battery in NCANDA. Corroboration of previous factor analysis models was obtained, in addition to the identification of an alternative factor model that has higher discriminant capacity for neuropsychological domains hypothesized to be most sensitive to alcohol exposure in human adolescents. The findings support the use of a factor model developed originally for the Penn CNB and a model developed specifically for the NCANDA project. The NCANDA 8-Factor Model has conceptual and empirical advantages that were identified in the current and prior studies. These advantages are particularly valuable when applied in alcohol research settings.

show abstract

Testing Measurement Invariance Across Groups in Longitudinal Data: Multigroup Second-Order Latent Growth Model

Cited by 25 publications

References 27 publications

Self-Esteem Trajectories and Their Social Determinants in Adolescents With Different Levels of Cognitive Ability

Self-Esteem Trajectories and Their Social Determinants in Adolescents With Different Levels of Cognitive Ability

Permutation randomization methods for testing measurement equivalence and detecting differential item functioning in multiple-group confirmatory factor analysis.

Comparison of factor analysis models applied to the NCANDA neuropsychological test battery

Contact Info

Product

Resources

About