Testing Measurement Invariance with Ordinal Missing Data: A Comparison of Estimators and Missing Data Techniques

Chen, Po‐Yi; Wu, Wei; Garnier‐Villarreal, Mauricio; Kite, Benjamin A.; Fan, Junwei

doi:10.1080/00273171.2019.1608799

Cited by 39 publications

(59 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This could also explain why the type I error rates from rFIML were conservative. Similar findings have been reported in previous research (e.g., Chen et al, 2019). Fourth, rFIML showed higher perfect recovery rates and power than WLSMV_PD in detecting non-uniform noninvariance (i.e., directions of non-invariance are different across non-invariant items) when missing data present.…”

Section: Major Findingssupporting

confidence: 89%

“…These methods include full information maximum likelihood (FIML), robust full information maximum likelihood (rFIML), and the mean and variance adjusted weighted least-squared method paired with pairwise deletion (WLSMV_PD) (e.g., Beam, Marcus, Turkheimer & Emery, 2018;Bou Malham & Saucier, 2014;Fokkema, Smits, Kelderman, & Cuijpers, 2013;Sommer, et al, 2019). Given that previous research has shown that rFIML outperformed FIML for ordinal data (e.g., Chen, Wu, Garnier-Villarreal, Kite & Jia, 2019), we only consider rFIML and WLSMV_PD in the current study.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Addressing missing data in specification search in measurement invariance testing with Likert-type scale variables: A comparison of two approaches

Chen

Brandt

et al. 2020

Behav Res

Self Cite

View full text Add to dashboard Cite

In measurement invariance testing, when a certain level of full invariance is not achieved, the sequential backward specification search method with the largest modification index (SBSS_LMFI) is often used to identify the source of non-invariance. SBSS_LMFI has been studied under complete data but not missing data. Focusing on Likert-type scale variables, this study examined two methods for dealing with missing data in SBSS_LMFI using Monte Carlo simulation: robust full information maximum likelihood estimator (rFIML) and mean and variance adjusted weighted least squared estimator coupled with pairwise deletion (WLSMV_PD). The result suggests that WLSMV_PD could result in not only over-rejections of invariance models but also reductions of power to identify non-invariant items. In contrast, rFIML provided good control of type I error rates, although it required a larger sample size to yield sufficient power to identify non-invariant items. Recommendations based on the result were provided.

show abstract

Section: Major Findingssupporting

confidence: 89%

Section: Introductionmentioning

confidence: 99%

Addressing missing data in specification search in measurement invariance testing with Likert-type scale variables: A comparison of two approaches

Chen

Brandt

et al. 2020

Behav Res

Self Cite

View full text Add to dashboard Cite

show abstract

“…In factor analysis, the investigation of measurement invariance (Millsap, 2011) is heavily discussed. It has been recommended that invariance analysis for ordinal variables should also treat variables as ordinal (Chen et al, 2020;Svetina et al, 2020). By continuing our arguments, we think that the assessment of invariance can be equally defended by treating ordinal variables as continuous.…”

Section: Discussionmentioning

confidence: 67%

Why Ordinal Variables Can (Almost) Always Be Treated as Continuous Variables: Clarifying Assumptions of Robust Continuous and Ordinal Factor Analysis Estimation Methods

Robitzsch

2020

Front. Educ.

219

View full text Add to dashboard Cite

“…In the modeling of factor structures, the investigation of measurement invariance (Millsap, 2011) is heavily discussed. It has been recommended that invariance analysis for ordinal variables should also treat variables as ordinal (Chen, Wu, Garnier-Villarreal, Kite, & Jia, 2020). By continuing our arguments, we think that the assessment of invariance can be equally defended by treating ordinal variables as continuous.…”

Section: Discussionmentioning

confidence: 70%

Why Ordinal Variables Can (Almost) Always be Treated as Continuous Variables: Clarifying Assumptions of Robust Continuous and Ordinal Factor Analysis Estimation Methods

Robitzsch¹

2020

Preprint

View full text Add to dashboard Cite

The analysis of factor structures is one of the most critical psychometric applications. Frequently, variables (i.e., items or indicators) resulting from questionnaires using ordinal items with 2 to 7 categories are used. There are plenty of articles that recommend treating ordinal variables in a factor analysis by default as ordinal and not as continuous imposing a multivariate normal distribution assumption. In this article, we critically reflect that the reasoning behind such suggestions is flawed. In our view, findings from simulation studies cannot tell about the right modeling strategy of ordinal variables in factor analysis. Moreover, it is argued that ordinal factor models impose a normality assumption for underlying continuous variables, which might also often be false in empirical applications. However, researchers seldom opt for these much-needed, more flexible modeling strategies if the ordinal nature variables would seriously be modeled in factor analysis. Finally, the consequences of modeling choices for validity, reliability, measurement invariance, and the assessment of global model fit are discussed.

show abstract

Testing Measurement Invariance with Ordinal Missing Data: A Comparison of Estimators and Missing Data Techniques

Abstract: This paper is NOT THE PUBLISHED VERSION; but the author's final, peer-reviewed manuscript. The published version may be accessed by following the link in th citation below.

Cited by 39 publications

References 33 publications

Addressing missing data in specification search in measurement invariance testing with Likert-type scale variables: A comparison of two approaches

Addressing missing data in specification search in measurement invariance testing with Likert-type scale variables: A comparison of two approaches

Why Ordinal Variables Can (Almost) Always Be Treated as Continuous Variables: Clarifying Assumptions of Robust Continuous and Ordinal Factor Analysis Estimation Methods

Why Ordinal Variables Can (Almost) Always be Treated as Continuous Variables: Clarifying Assumptions of Robust Continuous and Ordinal Factor Analysis Estimation Methods

Contact Info

Product

Resources

About