Multilevel Dynamic Generalized Structured Component Analysis for Brain Connectivity Analysis in Functional Neuroimaging Data

• Published in: Psychometrika Vol. 81; no. 2; pp. 565 - 581
• Main Authors: Jung, Kwanghee, Takane, Yoshio, Hwang, Heungsun, Woodward, Todd S.
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.06.2016; Springer Nature B.V
• Subjects: Algorithms; Assessment; Behavioral Science and Psychology; Brain; Brain - physiology; Brain - physiopathology; Case-Control Studies; Experimental Groups; Functional Neuroimaging; Hemodynamics; Humanities; Humans; Law; Least Squares Statistics; Least-Squares Analysis; Magnetic Resonance Imaging; Medical imaging; Memory, Short-Term - physiology; Multilevel Analysis; Neuroimaging; Parameter estimation; Principal Component Analysis; Psychology; Psychometrics; Schizophrenia - physiopathology; Statistical Theory and Methods; Statistics as Topic; Statistics for Social Sciences; Structural equation modeling; Structural Equation Models; Testing and Evaluation; Time series; Variables; multilevel analysis; alternating least squares (ALS) algorithm; brain connectivity analysis; structural equation modeling; time series data; generalized structured component analysis; functional neuroimaging; multi-subject data
• ISSN: 0033-3123; 1860-0980; 1860-0980
• DOI: 10.1007/s11336-015-9440-6

We extend dynamic generalized structured component analysis (GSCA) to enhance its data-analytic capability in structural equation modeling of multi-subject time series data. Time series data of multiple subjects are typically hierarchically structured, where time points are nested within subjects who are in turn nested within a group. The proposed approach, named multilevel dynamic GSCA, accommodates the nested structure in time series data. Explicitly taking the nested structure into account, the proposed method allows investigating subject-wise variability of the loadings and path coefficients by looking at the variance estimates of the corresponding random effects, as well as fixed loadings between observed and latent variables and fixed path coefficients between latent variables. We demonstrate the effectiveness of the proposed approach by applying the method to the multi-subject functional neuroimaging data for brain connectivity analysis, where time series data-level measurements are nested within subjects.