Path and Direction Discovery in Individual Dynamic Factor Models: A Regularized Hybrid Unified Structural Equation Modeling with Latent Variable
Year: 2022
Type: preprint
Abstract: There has been an increasing call to model multivariate time series data with measurement error. The combination of latent factors with a vector autoregressive (VAR) model leads to the dynamic factor model (DFM), in which dynamic relations are derived within factor series, among factors and observed time series, or both. However, a few limitations exist in the DFM representatives and estimation: 1) the dynamic component of DFM contains either directed or undirected contemporaneous relations, but not both, 2) selecting the optimal model in exploratory DFM is a challenge, 3) the consequences of structural misspecifications on estimation and model selection is barely studied. Our paper serves to advance DFM with a hybrid VAR representations and the utilization of LASSO regularization to select the dynamnic relations in a data-driven manner. A simulation study is presented to investigate the sensitivity of finding the true hybird dynamic relations in the structural model and the specificity of excluding the false relations using LASSO-regularization versus pseudo-ML. We also examine the robustness of parameter estimates in the selected model using LASSO-regularization, pseudo-ML, and model-implied instrumental variable two-stage least squares estimation. We aim to offer researchers guidance on model selection and estimation in person-centered dynamic assessments.
Authors: Ai Ye, Kenneth A. Bollen
Language: English
Field: Decision Sciences
Domain: Social Sciences
Open Access status: green
OpenAlex ID: W4312069508