Limitations Of Vector Autoregressive Models

potentially important in a structural vector autoregressive (SVAR) model. Univariate autoregression. Greater ability to account for unit roots. The impulse response coe cients are obtained from an autoregression in each variable of interest augmented with current and lagged values of the identi ed common shocks. VAR models generalize the univariate autoregressive model by allowing for more than one evolving variable. Thereby they account for Sims’ critique that the exogeneity assumptions for some of the variables in simultaneous equations models are ad hoc and often not backed by fully developed theories. The primary contribution of this paper is to develop exible methods for incorporating a range of parameter restrictions in Markov-Switching Vector Autogression (MS-VAR) and Bayesian Vector Autoregression (BVAR) models. •More generally we might want to consider models for more than on variable. Using dynamic vector autoregressive model, the results show a correlations and causalities of bond's return in ASEAN, China, Japan and United States. class: center, middle, inverse, title-slide # Structural vector autoregressive models ### Kevin Kotzé ---