|Institution:||University of Georgia|
|Full text PDF:||http://purl.galileo.usg.edu/uga_etd/fan_yi_201508_ms|
This study evaluated a neglected parameterization approach by Rindskof (1984) and its application to analyzing Multitrait-Multimethod (MTMM) data. Through taking analyses on a Monte Carlo simulation study and a large review of MTMM studies, I examined the Rindskopf raparameterization model (CTCM-R model) and compared its performance with the other two widely applied CFA-MTMM models, namely, the correlated trait-correlated method model (CTCM) and the correlated trait-correlated uniqueness model (CTCU), in regards to their convergence, admissibility, model fit, and parameter estimation biases. Results from analyzing both simulated MTMM data and previous published MTMM data showed that the CTCM-R model serves as a favorable alternative approach to MTMM studies. Advisors/Committee Members: Nathan Carter.