Measurement Invariance and Differential Item Functioning in Latent Class Analysis With Stepwise Multiple Indicator Multiple Cause Modeling

By Katherine E. Masyn. 2017

117 citations recorded by the source corpus.

The use of latent class analysis, and finite mixture modeling more generally, has become almost commonplace in social and health science domains. Typically, research aims in mixture model applications include investigating predictors and distal outcomes of latent class membership. The most recent developments for incorporating latent class antecedents and consequences are stepwise procedures that decouple the classification and prediction models. It was initially believed these procedures might avoid the potential misspecification bias in the simultaneous models that include both latent class indicators and predictors. However, if direct effects from the predictors to the indicators are omitted in the stepwise procedure, the prediction model can yield biased estimates. This article presents a logical and principled approach, readily implemented in current software, to testing for direct effects from latent class predictors to indicators using multiple indicator multiple cause modeling. This approach is illustrated with real data and opportunities for future developments are discussed.

Subfields: Health, Statistics and Probability

View Paper: https://www.semanticscholar.org/paper/6fbe989ca1e1ced7f2826ccc51d21ae297c4fd14

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Health

1. Margarita Olivera‐Aguilar
2. Samuel Rikoon
3. Karen Nylund-Gibson
4. Ryan P. Grimm

In Statistics and Probability

1. E. W. G. Moore
2. D. Hull
3. Sarah Ferguson
4. Karen Nylund-Gibson
5. Ryan P. Grimm
6. Margarita Olivera‐Aguilar
7. Samuel Rikoon
8. Katherine E. Masyn

Citations in the corpus

• Finding latent groups in observed data: A primer on latent profile analysis in Mplus for applied researchers (2020, background): “To learn more about this approach, see Masyn (2017) and Osterlind and Everson (2009).”
• Prediction from Latent Classes: A Demonstration of Different Approaches to Include Distal Outcomes in Mixture Models (2019, methodology): “Class enumeration for these five items is detailed in the Masyn (2017) paper. Once the unconditional model was identified, DIF was explored with respect to gender. For the distal comparisons discussed in this paper, we begin with a 4-class LCA with DIF based on the Masyn (2017) paper.”
• Assessing Measurement Invariance in Multiple-Group Latent Profile Analysis (2018, methodology): “That is, the procedure described by Masyn (2017) does not inform the ability of model fit indexes to detect measurement noninvariance between subgroups in the overall model (one goal of this study).”
• Ten Frequently Asked Questions About Latent Class Analysis (2018, unknown): “For example, recent work on differential item functioning (DIF) in the LCA context (e.g., the direct association of a covariate and a latent class indicator) has presented modeling strategies for permitting DIF and including it in subsequent three-step specifications (Masyn, 2017).”