手法を比較

	条件付きプロセス分析（媒介変数の調整）	ベイズ構造方程式モデリング（BSEM）	最小二乗法 (OLS) 回帰
分野	因果推論	ベイズ	計量経済学
系統	Regression model	Bayesian methods	Regression model
提唱年	2018	2012	2019
提唱者	Andrew F. Hayes (PROCESS framework); Preacher, Rucker & Hayes (moderated mediation)	Bengt Muthén & Tihomir Asparouhov	Wooldridge (textbook treatment); classical least squares
種類	Regression-based conditional process model	Bayesian latent variable model	Linear regression
原典	Hayes, A. F. (2018). Introduction to Mediation, Moderation, and Conditional Process Analysis: A Regression-Based Approach (2nd ed.). The Guilford Press. ISBN: 978-1462534654	Muthén, B. & Asparouhov, T. (2012). Bayesian SEM: A More Flexible Representation of Substantive Theory. Psychological Methods, 17(3), 313–335.	Wooldridge, J. M. (2019). Introductory Econometrics: A Modern Approach (7th ed.). Cengage Learning. ISBN: 978-1337558860
別名	moderated mediation, moderated mediation analysis, PROCESS model, Hayes PROCESS conditional process model	BSEM, Bayesian latent variable model, approximate zero constraints SEM, Bayesçi Yapısal Eşitlik Modeli	ordinary least squares, classical linear regression, linear regression, en küçük kareler regresyonu
関連	5	6	5
概要	Conditional process analysis is Andrew F. Hayes's regression-based PROCESS framework (2018) that combines mediation and moderation in a single model, testing how an indirect effect changes across levels of a moderator. It quantifies conditional indirect and conditional direct effects and tests them with bootstrap confidence intervals.	Bayesian SEM, introduced by Muthén and Asparouhov in 2012, extends classical structural equation modeling by placing prior distributions on factor loadings, path coefficients, and covariances. Instead of returning a single maximum-likelihood estimate, it uses Markov chain Monte Carlo to produce a full posterior distribution for every parameter, enabling principled uncertainty quantification in models with latent variables.	Ordinary Least Squares is the classical linear regression method that explains a continuous outcome as a linear combination of predictors. It estimates the coefficients by minimising the sum of squared residuals, and under the Gauss-Markov assumptions these estimates are the best linear unbiased estimator (BLUE).