Salguiero, Maria de Fátima, Smith, Peter W. F. and McDonald, John W.
Connections between single-factor analysis and graphical Gaussian models. Southampton, UK, Southampton Statistical Sciences Research Institute, 13pp.
(S3RI Methodology Working Papers, M06/13).
The classical single-factor model is parametrized as a graphical Gaussian model. The relationship between the classical parametrization of the single-factor model and this alternative parametrization is derived. This relationship provides extra insights into the single-factor model, which facilitates power calculations. The overall power of the first step of a backward elimination model selection procedure to detect an association structure between manifest variables compatible with a single-factor model is investigated. The results are illustrated using a one-factor congeneric measurement model.
Actions (login required)