Investigating Factorial Invariance of Latent Variables Across Populations When Manifest Variables Are Missing Completely

Content Provider	Scilit
Author	Widaman, Keith F. Grimm, Kevin J. Early, Dawnté R. Robins, Richard W. Conger, Rand D.
Copyright Year	2013
Description	Difficulties arise in multiple-group evaluations of factorial invariance if particular manifest variables are missing completely in certain groups. Ad hoc analytic alternatives can be used in such situations (e.g., deleting manifest variables), but some common approaches, such as multiple imputation, are not viable. At least 3 solutions to this problem are viable: analyzing differing sets of variables across groups, using pattern mixture approaches, and a new method using random number generation. The latter solution, proposed in this article, is to generate pseudo-random normal deviates for all observations for manifest variables that are missing completely in a given sample and then to specify multiple-group models in a way that respects the random nature of these values. An empirical example is presented in detail comparing the 3 approaches. The proposed solution can enable quantitative comparisons at the latent variable level between groups using programs that require the same number of manifest variables in each group.
Related Links	http://europepmc.org/articles/pmc3765030?pdf=render https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3765030/pdf
Ending Page	408
Page Count	25
Starting Page	384
ISSN	10705511
e-ISSN	15328007
DOI	10.1080/10705511.2013.797819
Journal	Structural Equation Modeling: A Multidisciplinary Journal
Issue Number	3
Volume Number	20
Language	English
Publisher	Informa UK Limited
Publisher Date	2013-07-01
Access Restriction	Open
Subject Keyword	Mathematical Social Sciences Confirmatory Factor Analysis Factorial Invariance Missing Data Structural Equation Modeling
Content Type	Text
Resource Type	Article
Subject	Sociology and Political Science Economics, Econometrics and Finance Decision Sciences Modeling and Simulation