השוואת שיטות

	מודל משוואות מבניות בייסיאני (BSEM)	ניתוח תיווך סיבתי (אפקטים ישירים ועקיפים טבעיים)	רגרסיית ריבועים פחותים רגילים (OLS)
תחום	בייסיאני	הסקה סיבתית	אקונומטריקה
משפחה	Bayesian methods	Regression model	Regression model
שנת המקור	2012	2010	2019
הוגה השיטה	Bengt Muthén & Tihomir Asparouhov	Pearl (2001); general framework by Imai, Keele & Tingley (2010)	Wooldridge (textbook treatment); classical least squares
סוג	Bayesian latent variable model	Counterfactual causal decomposition	Linear regression
מקור מכונן	Muthén, B. & Asparouhov, T. (2012). Bayesian SEM: A More Flexible Representation of Substantive Theory. Psychological Methods, 17(3), 313–335.	Pearl, J. (2001). Direct and Indirect Effects. In Proceedings of the Seventeenth Conference on Uncertainty in Artificial Intelligence (UAI), 411-420.	Wooldridge, J. M. (2019). Introductory Econometrics: A Modern Approach (7th ed.). Cengage Learning. ISBN: 978-1337558860
כינויים	BSEM, Bayesian latent variable model, approximate zero constraints SEM, Bayesçi Yapısal Eşitlik Modeli	natural direct effect, natural indirect effect, NDE / NIE decomposition, counterfactual mediation	ordinary least squares, classical linear regression, linear regression, en küçük kareler regresyonu
קשורות	6	5	5
תקציר	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.	Causal mediation analysis is a counterfactual framework that splits a treatment's total effect into a Natural Direct Effect (NDE) and a Natural Indirect Effect (NIE) that runs through a mediator. The modern general approach was formalised by Pearl (2001) and Imai, Keele and Tingley (2010), giving the decomposition a precise causal interpretation.	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).