Published In
Structural Equation Modeling-A Multidisciplinary Journal
Document Type
Article
Publication Date
5-25-2026
Subjects
Attrition, bayesian estimation, missing data, Monte Carlo simulation, weighted least squares
Abstract
A Monte Carlo simulation was used to evaluate the performance of latent growth curve (LGC) modelswith binary observed variables when the attrition pattern was missing not at random (MNAR) for fivetime points. Parameter and standard error biases for three estimation methods were compared:weighted least squares with mean and variance adjustment (WLSMV), categorical robust marginal max-imum likelihood (categorical MLR), and Bayes. The results indicated that robust diagonal weightedleast squares paired with multiple imputation (MI) performed best when values were missing at ran-dom. When data were missing not at random, Bayesian estimates performed best.
Rights
Copyright (c) 2026 The Authors Creative Commons License This work is licensed under a Creative Commons Attribution 4.0 International License.
DOI
10.1080/10705511.2026.2667459
Persistent Identifier
https://archives.pdx.edu/ds/psu/44741
Citation Details
Newsom, J. T., Keller, B. T., Kroeck, M. R., & Smith, N. A. (2026). The Impact of MNAR Attrition on Estimation of Latent Growth Curve Models with Binary Observed Variables. Structural Equation Modeling: A Multidisciplinary Journal, 1–11.