Порівняння методів

	Модель стійкого векторного авторегресійного аналізу (Robust VAR)	Квантильний ВАР (VAR)	Модель векторної авторегресії (VAR)
Галузь	Економетрика	Економетрика	Економетрика
Родина	Regression model	Regression model	Regression model
Рік появи	1980s–2000s	2006	2005
Автор методу	Extensions by Lutkepohl and others building on Sims (1980) VAR framework	Koenker and Xiao	Lütkepohl (textbook treatment); Sims (1980) macroeconometric tradition
Тип	Multivariate time-series model with robust estimation	Distribution impulse response	Multivariate time-series model
Основоположне джерело	Goncalves, S., & Kilian, L. (2004). Bootstrapping autoregressions with conditional heteroskedasticity of unknown form. Journal of Econometrics, 123(1), 89-120.	Koenker, R., & Xiao, Z. (2006). Quantile autoregression. Journal of the American Statistical Association, 101(475), 980-990.	Lütkepohl, H. (2005). New Introduction to Multiple Time Series Analysis. Springer.
Інші назви	robust VAR, outlier-robust VAR, heavy-tailed VAR, RVAR	Quantile-based impulse response	vector autoregression, VAR, VAR Modeli (Vektör Otoregresyon), vektör otoregresyon
Пов'язані	5	3	4
Підсумок	The Robust VAR model extends the classical Vector Autoregression framework by replacing ordinary least squares estimation with robust estimators — such as M-estimators or median-based methods — to reduce the influence of outliers, structural breaks, and heavy-tailed shocks common in financial and macroeconomic time series.	Quantile VAR estimates impulse responses of multivariate systems conditional on different quantiles of the distribution, revealing how shocks propagate heterogeneously across the conditional distribution. Introduced by Koenker and Xiao (2006) and applied to risk measurement by White et al. (2015), it reveals tail behavior and contagion effects invisible to mean-based VAR analysis. This is essential for risk management and understanding how crises propagate differently than normal times.	Vector Autoregression is a multivariate time-series model that treats several interdependent series symmetrically, letting each variable depend on its own past values and the past values of all the others. It is the standard tool for capturing mutual causality and joint dynamics, developed in the modern multiple-time-series tradition treated by Lütkepohl (2005).