Comparer des méthodes

	Modèle de VAR structurel bayésien (B-SVAR)	Test des bornes bayésien ARDL
Domaine	Économétrie	Économétrie
Famille	Regression model	Regression model
Année d'origine	1998–2005	2001 (ARDL); Bayesian extension 2010s
Auteur d'origine	Sims & Zha (1998); Uhlig (2005) for sign-restriction identification	Pesaran, Shin & Smith (ARDL framework, 2001); Bayesian adaptation by subsequent literature
Type	Structural multivariate time-series model	Cointegration / bounds testing
Source fondatrice	Sims, C. A., & Zha, T. (1998). Bayesian methods for dynamic multivariate models. International Economic Review, 39(4), 949–968.	Pesaran, M. H., Shin, Y., & Smith, R. J. (2001). Bounds testing approaches to the analysis of level relationships. Journal of Applied Econometrics, 16(3), 289-326.
Alias	Bayesian SVAR, B-SVAR, Bayesian structural VAR, Bayesian identified VAR	Bayesian ARDL, Bayesian bounds testing approach, Bayes ARDL cointegration, Bayesian PSS bounds test
Apparentées	6	5
Résumé	The Bayesian Structural Vector Autoregression model combines the structural identification of SVAR with Bayesian prior distributions over parameters. It estimates causal impulse responses between multiple time series while incorporating prior economic knowledge and producing full posterior uncertainty bands rather than point estimates alone.	The Bayesian ARDL Bounds Test extends the classical Pesaran-Shin-Smith (2001) bounds testing approach to cointegration by embedding it within a Bayesian inferential framework. Instead of relying on frequentist F- and t-statistics with tabulated critical values, the researcher specifies prior distributions on the model parameters and derives posterior evidence of a long-run level relationship between variables that may be integrated of order zero or one.