Noniterative Estimation and the Choice of the Number of Factors in Exploratory Factor Analysis
- 1 June 1990
- journal article
- Published by Cambridge University Press (CUP) in Psychometrika
- Vol. 55 (2) , 277-291
- https://doi.org/10.1007/bf02295288
Abstract
Based on the usual factor analysis model, this paper investigates the relationship between improper solutions and the number of factors, and discusses the properties of the noniterative estimation method of Ihara and Kano in exploratory factor analysis. The consistency of the Ihara and Kano estimator is shown to hold even for an overestimated number of factors, which provides a theoretical basis for the rare occurrence of improper solutions and for a new method of choosing the number of factors. The comparative study of their estimator and that based on maximum likelihood is carried out by a Monte Carlo experiment.Keywords
This publication has 27 references indexed in Scilit:
- Factor Analysis and AICPsychometrika, 1987
- Nonconvergence, Improper Solutions, and Starting Values in Lisrel Maximum Likelihood EstimationPsychometrika, 1985
- The Effect of Sampling Error on Convergence, Improper Solutions, and Goodness-of-Fit Indices for Maximum Likelihood Confirmatory Factor AnalysisPsychometrika, 1984
- COVARIANCE STRUCTURESPublished by Cambridge University Press (CUP) ,1982
- A new look at the statistical model identificationIEEE Transactions on Automatic Control, 1974
- An Empirical Study of the Factor Analysis Stability HypothesisPsychometrika, 1961
- Recent Trends in Factor AnalysisJournal of the Royal Statistical Society. Series A (General), 1961
- FACTOR ANALYSIS BY LAWLEY'S METHOD OF MAXIMUM LIKELIHOODBritish Journal of Statistical Psychology, 1949
- Fundamental Factors of Comprehension in ReadingPsychometrika, 1944
- VI.—The Estimation of Factor Loadings by the Method of Maximum LikelihoodProceedings of the Royal Society of Edinburgh, 1940