Large vector auto regressions

Arbeitspapier

One popular approach for nonstructural economic and financial forecasting is to include a large number of economic and financial variables, which has been shown to lead to significant improvements for forecasting, for example, by the dynamic factor models. A challenging issue is to determine which variables and (their) lags are relevant, especially when there is a mixture of serial correlation (temporal dynamics), high dimensional (spatial) dependence structure and moderate sample size (relative to dimensionality and lags). To this end, an integrated solution that addresses these three challenges simultaneously is appealing. We study the large vector auto regressions here with three types of estimates. We treat each variable's own lags different from other variables' lags, distinguish various lags over time, and is able to select the variables and lags simultaneously. We first show the consequences of using Lasso type estimate directly for time series without considering the temporal dependence. In contrast, our proposed method can still produce an estimate as efficient as an oracle under such scenarios. The tuning parameters are chosen via a data driven 'rolling scheme' method to optimize the forecasting performance. A macroeconomic and financial forecasting problem is considered to illustrate its superiority over existing estimators.

Angaben zum Objekt

• Sprache: Englisch

Verweise und Beziehungen

• Erschienen in: Series: SFB 649 Discussion Paper ; No. 2011-048

Klassifikation und Themen

• Klassifikation: Wirtschaft ; Estimation: General ; Semiparametric and Nonparametric Methods: General ; Multiple or Simultaneous Equation Models: Time-Series Models; Dynamic Quantile Regressions; Dynamic Treatment Effect Models; Diffusion Processes; State Space Models ; Prices, Business Fluctuations, and Cycles: General (includes Measurement and Data) ; Money and Interest Rates: General ; General Financial Markets: General (includes Measurement and Data)
• Thema: time series ; Vector Auto Regression ; regularization ; lasso ; group lasso ; oracle estimator ; VAR-Modell ; Zeitreihenanalyse ; Theorie

Beteiligte, Orts- und Zeitangaben

• Ereignis: Geistige Schöpfung
• (wer): Song, Song ; Bickel, Peter J.
• Ereignis: Veröffentlichung
• (wer): Humboldt University of Berlin, Collaborative Research Center 649 - Economic Risk
• (wo): Berlin
• (wann): 2011

Weitere Informationen

• Handle: http://hdl.handle.net/10419/56649
• Letzte Aktualisierung: 10.03.2025, 11:44 MEZ