|
on Econometric Time Series |
| By: | Helmut Lütkepohl; George Milunovich |
| Abstract: | Changes in residual volatility in vector autoregressive (VAR) models can be used for identifying structural shocks in a structural VAR analysis. Testable conditions are given for full identification for the case where the volatility changes can be modelled by a multivariate GARCH process. Formal statistical tests are presented for identification and their small sample properties are investigated via a Monte Carlo study. The tests are applied to investigate the validity of the identification conditions in a study of the effects of U.S. monetary policy on exchange rates. It is found that the data do not support full identification in most of the models considered, and the implied problems for the interpretation of the results are discussed. |
| Keywords: | Structural vector autoregression, conditional heteroskedasticity, GARCH, identification via heteroskedasticity |
| JEL: | C32 |
| Date: | 2015 |
| URL: | http://d.repec.org/n?u=RePEc:diw:diwwpp:dp1455&r=ets |
| By: | Berg, Tim Oliver |
| Abstract: | In this paper I assess the ability of Bayesian vector autoregressions (BVARs) and dynamic stochastic general equilibrium (DSGE) models of different size to forecast comovements of major macroeconomic series in the euro area. Both approaches are compared to unrestricted VARs in terms of multivariate point and density forecast accuracy measures as well as event probabilities. The evidence suggests that BVARs and DSGE models produce accurate multivariate forecasts even for larger datasets. I also detect that BVARs are well calibrated for most events, while DSGE models are poorly calibrated for some. In sum, I conclude that both are useful tools to achieve parameter dimension reduction. |
| Keywords: | BVARs, DSGE Models, Multivariate Forecasting, Large Dataset, Simulation Methods, Euro Area |
| JEL: | C11 C52 C53 E37 |
| Date: | 2015–02–24 |
| URL: | http://d.repec.org/n?u=RePEc:pra:mprapa:62405&r=ets |
| By: | Gian Piero Aielli; Massimiliano Caporin (University of Padova) |
| Abstract: | The OGARCH specification is the leading model for a class of multivariate GARCH (MGARCH)specifications that are based on linear combinations of univariate GARCH specifications. Most MGARCH models in this class adopt a spectral decomposition of the covariance matrix, allowing for heteroskedasticity on at least some of the principal components, while the loading matrix, which maps the conditional principal components to the asset returns, is constant over time. This paper extends the OGARCH model class to allow for time-varying loadings. Our approach closely parallels the DCC modelling approach, introduced as an extension of the CCC model, to allow for dynamic correlations. After introducing an auxiliary process that captures the relevant features of the unobservable loading dynamics, we compute the time-varying loading matrix from the auxiliary process, subject to the necessary orthonormality constraints. The resulting model (the Dynamic Principal Components, or DPC, model) preserves the OGARCH models ease of interpretation and feasibility. In particular, we show that the eigenvectors of the sample covariance matrix can consistently estimate the time-varying loadings intercept term. This property extends to the dynamic framework the well-known analogous property of the OGARCH model. Empirical examples demonstrate the benefits to the loading matrix of introducing time-varying properties. |
| Keywords: | Spectral Decomposition, Principal Component Analysis, Orthogonal GARCH, Scalar BEKK, DCC, Multivariate GARCH, Two-step Estimation. |
| JEL: | C32 C58 C13 G10 |
| Date: | 2015–02 |
| URL: | http://d.repec.org/n?u=RePEc:pad:wpaper:0194&r=ets |