|
on Econometric Time Series |
| By: | Martin Bruns; Helmut Lütkepohl |
| Abstract: | We propose a test for time-varying impulse responses in heteroskedastic structural vector autoregressions that can be used when the shocks are identified by external proxy variables as a group. The test can be used even if the shocks are not identified individually. The asymptotic analysis is supported by small sample simulations which show good properties of the test. An investigation of the impact of productivity shocks in a small macroeconomic model for the U.S. illustrates the importance of the issue for empirical work. |
| Keywords: | Structural vector autoregression, proxy VAR, heteroskedasticity, productivity shocks |
| JEL: | C32 |
| Date: | 2022 |
| URL: | http://d.repec.org/n?u=RePEc:diw:diwwpp:dp2005&r= |
| By: | Bauwens, Luc (Université catholique de Louvain, LIDAM/CORE, Belgium); Chevillon, Guillaume; Laurent, Sébastien |
| Abstract: | We build on two contributions that have found conditions for large dimensional networks or systems to generate long memory in their individual components, and provide a methodology for modeling and forecasting series displaying long range dependence. We model long memory properties within a vector autoregressive system of order 1 and consider Bayesian estimation or ridge regression. For these, we derive a theory-driven parametric setting that informs a prior distribution or a shrinkage target. Our proposal significantly outperforms univariate time series long memory models when forecasting a daily volatility measure for 250 US company stocks, as well as seasonally adjusted monthly streamflow series recorded at 97 locations of the Columbia river basin. |
| Keywords: | Bayesian estimation ; Ridge regression ; Vector autoregressive model ; Forecasting |
| Date: | 2022–04–03 |
| URL: | http://d.repec.org/n?u=RePEc:cor:louvco:2022016&r= |
| By: | Daniel Hopp |
| Abstract: | Nowcasting can play a key role in giving policymakers timelier insight to data published with a significant time lag, such as final GDP figures. Currently, there are a plethora of methodologies and approaches for practitioners to choose from. However, there lacks a comprehensive comparison of these disparate approaches in terms of predictive performance and characteristics. This paper addresses that deficiency by examining the performance of 12 different methodologies in nowcasting US quarterly GDP growth, including all the methods most commonly employed in nowcasting, as well as some of the most popular traditional machine learning approaches. Performance was assessed on three different tumultuous periods in US economic history: the early 1980s recession, the 2008 financial crisis, and the COVID crisis. The two best performing methodologies in the analysis were long short-term memory artificial neural networks (LSTM) and Bayesian vector autoregression (BVAR). To facilitate further application and testing of each of the examined methodologies, an open-source repository containing boilerplate code that can be applied to different datasets is published alongside the paper, available at: github.com/dhopp1/nowcasting_benchmark. |
| Date: | 2022–05 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2205.03318&r= |