방법 비교

	확인적 요인 분석 (CFA)	탐색적 요인 분석 (EFA)	주성분 분석
분야	심리측정학	통계학	머신러닝
계열	Latent structure	Latent structure	Machine learning
기원 연도	1969	—	2002
창시자	Karl Gustav Jöreskog	—	Jolliffe, I.T. (textbook); Pearson & Hotelling (origins)
유형	Hypothesis-testing latent variable model	Latent variable / dimension reduction	Unsupervised dimensionality reduction
원전	Jöreskog, K. G. (1969). A general approach to confirmatory maximum likelihood factor analysis. Psychometrika, 34(2), 183–202.	Fabrigar, L. R., Wegener, D. T., MacCallum, R. C. & Strahan, E. J. (1999). Evaluating the use of exploratory factor analysis in psychological research. Psychological Methods, 4(3), 272–299.	Jolliffe, I.T. (2002). Principal Component Analysis (2nd ed.). Springer.
별칭	CFA, confirmatory FA, measurement model, restricted factor analysis	common factor analysis, açımlayıcı faktör analizi, factor analysis	Temel Bileşenler Analizi (PCA), PCA, principal components analysis, Karhunen-Loève transform
관련	4	4	3
요약	Confirmatory factor analysis tests a researcher-specified factor structure against observed data. Unlike exploratory approaches, the researcher decides in advance which indicators load on which latent factor, and the model is evaluated by how closely the implied covariance matrix reproduces the sample covariance matrix. CFA is central to scale validation, construct validity assessment, and measurement invariance testing.	Exploratory factor analysis reduces a large set of observed variables into a smaller number of latent common factors. It is widely used in scale development and psychometrics to uncover the dimensional structure that underlies a set of correlated items, without specifying that structure in advance.	Principal Component Analysis (PCA) is an unsupervised dimensionality-reduction method — given its modern textbook treatment by Ian Jolliffe (2002) — that compresses high-dimensional data into fewer dimensions while preserving the maximum possible variance. It re-expresses correlated variables as a small set of uncorrelated principal components ordered by how much of the data's variation each one captures.