A study of an identification problem and substitute use of principal component analysis in factor analysis

DOI10.32917/HMJ/1206128499MaRDI QIDQ1210046zbMATH OpenOpenAlexFDO

Authors Manabu Sato

Publication date 16 May 1993

Published in Hiroshima Mathematical Journal (Search for Journal in Brave)

Full work available at URL https://doi.org/10.32917/hmj/1206128499, https://projecteuclid.org/journals/hiroshima-mathematical-journal/volume-22/issue-3/A-study-of-an-identification-problem-and-substitute-use-of/10.32917/hmj/1206128499.full

zbMATH Keywords

adequacy problem of principal components analysisexistence of a decompositionfactor analysis modelidentification problemmonofactor casesmultifactor casesuniqueness of the decomposition

Mathematics Subject Classification ID

Factor analysis and principal components; correspondence analysis (62H25)

Review text

Part I treats an identification problem of the Factor Analysis (FA) model. This problem is fundamental and important. In Section 1, the identification problem is described in detail. In section 2, the existence of a decomposition is discussed. In Section 3, uniqueness of the decompositions is discussed. The author attempted to study this problem systematically and some new results are obtained. Part II deals with an adequacy problem of Principal Components Analysis (PCA) as substitute use for FA. In practice, PCA is very often for the same purpose as FA without careful consideration. In Section 4, an approach of investigating PCA as a substitute for FA is introduced. In Section 5, monofactor cases are treated. Finally, in Section 6, multifactor cases are treated. The present paper tries to clarify proper use of PCA as a substitute for FA.

Recommendations

• scientific article; zbMATH DE number 4161975
• Factor analysis and principal components
• scientific article; zbMATH DE number 29835
• Some inequalities contrasting principal component and factor analyses solutions
• Theoretical Justification of Decision Rules for the Number of Factors: Principal Component Analysis as a Substitute for Factor Analysis in One-Factor Cases

Cited in

(11)

• Bayesian exploratory factor analysis
• Some relationships between factors and components
• Oblique factors and components with independent clusters
• Misconceptions and misunderstandings (M\&M) of exploratory factor analysis: some clarifications
• scientific article; zbMATH DE number 4161975 (Why is no real title available?)
• Theoretical Justification of Decision Rules for the Number of Factors: Principal Component Analysis as a Substitute for Factor Analysis in One-Factor Cases
• scientific article; zbMATH DE number 7387188 (Why is no real title available?)
• The validity of the linear model as a basis for extracting principal components from psychological variables
• Cover it up! Bipartite graphs uncover identifiability in sparse factor analysis
• Identifiable sparse Bayesian factorizations via meta regression
• Exploratory factor and principal component analyses: some new aspects

This page was built for publication: A study of an identification problem and substitute use of principal component analysis in factor analysis

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1210046)