Psychometric dynamic factor models for the analysis of longitudinally intensive data
Metadata[+] Show full item record
[ACCESS RESTRICTED TO THE UNIVERSITY OF MISSOURI AT AUTHOR'S REQUEST.] Dynamic factor model (DFM), a factor analytic approach developed for the analysis of intra-individual time series data, can be estimated using common structural equation modeling software. The thesis proposes that an independent Random Intercept is an intermediary factor structure between the traditional n and n+1 factor structures researchers could consider in the view of psychological measurement. In addition to allowing researchers to specify complex factor structures for change over time, which do not correspond to traditional notions of simple structure, the random intercept measurement model may constitute an attractive alternative to traditional factor models when data are well summarized by more parsimonious models. Simulations on random intercept DFM were conducted, and the model was applied to a real-world data..
Access is limited to the University of Missouri - Columbia.