Open AccessESTIMATION AND HYPOTHESIS‐TESTING FOR A GENERALIZED FACTOR ANALYSIS BASED ON RESIDUAL COVARIANCE MATRICES OF PRESCRIBED STRUCTURE 1
Author(s) -
McDonald R. P.
Publication year - 1970
Publication title -
ets research bulletin series
Language(s) - English
Resource type - Journals
eISSN - 2333-8504
pISSN - 0424-6144
DOI - 10.1002/j.2333-8504.1970.tb00592.x
Subject(s) - covariance , residual , mathematics , likelihood ratio test , covariance matrix , restricted maximum likelihood , maximum likelihood , statistics , factor analysis , econometrics , algorithm
ABSTRACT In a generalized factor model based on residual covariance matrices of prescribed structure, maximum likelihood estimates of the model parameters, and a likelihood‐ratio test of the number of major factors postulated, are obtained as the obvious generalized counterparts of the corresponding quantities in the classical common factor model, with the exception that there does not seem to be a suitable counterpart to Jöreskog's treatment of the problem of improper solutions in the classical case.