Structural Vector Autoregressions

By Lutz Kilian. 2011

181 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/61051b0ed875dfec370070d3336dcf8138e9540e

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Economics and Econometrics

Citations in the corpus

Granger Causality: A Review and Recent Advances (2021, background): “This more general form of (2) is known as a structural vector auto-regressive (SVAR) model (Kilian, 2013), and can be identiﬁed under certain parameter restrictions (Kilian and L¨utkepohl, 2017).”
Identification and estimation of non-Gaussian structural vector autoregressions (2015, methodology): “Identification by explicitly modeling conditional heteroskedasticity of the errors in various forms, considered by Normandin and Phaneuf (2004), Lanne et al. (2010), and Lütkepohl and Netšunajev (2014b), is also covered by our approach.”
Oil Price Shocks and the Stock Market: Evidence from Japan (2013, background): “Empirically however it turns out that the unrestricted estimate of is close to zero 10 thus making this b point moot (Kilian, 2012).”
DYNOTEARS: Structure Learning from Time-Series Data (2020, methodology): “We model the data using the following standard SVAR model (Demiralp and Hoover, 2003; Kilian, 2011; Swan-Pamﬁl son and Granger, 1997): for t ∈ { p, . . . the , T } and for all m ∈ { 1 , . . . z , M } , where p is autoregressive order , and m,t is a vector of centered error variables, which are…”
Joint Confidence Sets for Structural Impulse Responses (2016, unknown): “Inoue, A., and L. Kilian (2013), “Inference on Impulse Response Functions in Structural VAR Models,” Journal of Econometrics, 177, 1-13.”
Panel Vector Autoregressive Models: A Survey (2013, unknown): “Then the estimated model would be y1t = (A11 +A13(I A33`) 1A31)y1t 1 + (A12 +A13(I A33`) 1A32)y2t 1 + e1t(47) y2t = (A21 +A23(I A33`) 1A31)y1t 1 + (A22 +A23(I A33`) 1A32)y2t 1 + e2t(48) where e1t = J11u1t + (I A33`) 1(J31u1t + J32u2t + J33u3t) (49) e2t = J21u1t + J22u2t + J23u3t + (I A33`) 1(J31u1t ”