手法を比較

	時間変動係数ファクター拡張VAR (Time-Varying Parameter Factor-Augmented VAR)	グローバルVAR
分野	計量経済学	計量経済学
系統	Regression model	Regression model
提唱年	2005	2004
提唱者	Bernanke, Boivin, and Eliasz	Pesaran, Schuermann, and Weiner
種類	Time-varying system	International system model
原典	Bernanke, B. S., Boivin, J., & Eliasz, P. S. (2005). Measuring monetary policy. Journal of Political Economy, 113(1), 161-208.	Pesaran, M. H., Schuermann, T., & Weiner, S. M. (2004). Modeling regional interdependencies using a global error-correcting macroeconometric model. Journal of Business and Economic Statistics, 22(2), 129-162.
別名	Dynamic factor model with time-varying parameters	GVAR, Multi-country VAR
関連	3	3
概要	TVP-FAVAR is a hybrid framework combining factor-augmented VARs with time-varying parameter estimation via Kalman filtering. Introduced by Bernanke et al. (2005) and refined by Primiceri (2005), it extracts latent economic factors (e.g., a 'common monetary policy shock') from high-dimensional data while allowing VAR coefficients to evolve stochastically over time. This framework captures both reduced-dimensionality patterns and structural instability, making it ideal for studying evolving policy regimes and shock dynamics.	Global VAR (GVAR) is a large-scale macroeconomic modeling framework linking multiple countries (or regions) via trade and financial channels, allowing shocks in one country to propagate through the global system. Introduced by Pesaran et al. (2004), it solves the curse of dimensionality in international VAR models by estimating country-specific VARs conditional on foreign variables, then solving a system linking all countries. This approach is invaluable for analyzing global spillovers and international policy coordination.