Konferenzbeitrag

Directed Graph and Variable Selection in Large Vector Autoregressive Models

to connected objects

We represent the dynamic relation among variables in vector autoregressive (VAR) models as directed graphs. Based on these graphs, we identify so-called strongly connected components (SCCs). Using this graphical representation, we consider the problem of variable selection. We use the relations among the strongly connected components to select variables that need to be included in a VAR if interest is in forecasting or impulse response analysis of a given set of variables. We show that the set of selected variables from the graphical method coincides with the set of variables that is multi-step causal for the variables of interest by relating the paths in the graph to the coefficients of the "direct" VAR representation. Empirical applications illustrate the usefulness of the suggested approach: Including the selected variables into a small US monetary VAR is useful for impulse response analysis as it avoids the well-known "price-puzzle". We also find that including the selected variables into VARs typically improves forecasting accuracy at short horizons.

Language
Englisch

Bibliographic citation
Series: Beiträge zur Jahrestagung des Vereins für Socialpolitik 2019: 30 Jahre Mauerfall - Demokratie und Marktwirtschaft - Session: Econometrics - Time Series ; No. A04-V3

Classification
Wirtschaft
Multiple or Simultaneous Equation Models: Time-Series Models; Dynamic Quantile Regressions; Dynamic Treatment Effect Models; Diffusion Processes; State Space Models
Model Construction and Estimation
Large Data Sets: Modeling and Analysis
Monetary Policy
Subject
Vector autoregression
Variable selection
Directed graphs
Multi-step causality
Forecasting
Impulse response analysis

Event
Geistige Schöpfung
(who)
Bertsche, Dominik
Brüggemann, Ralf
Kascha, Christian
Event
Veröffentlichung
(who)
ZBW - Leibniz-Informationszentrum Wirtschaft
(where)
Kiel, Hamburg
(when)
2019

Handle
Last update
10.03.2025, 11:41 AM CET

Data provider

This object is provided by:
ZBW - Deutsche Zentralbibliothek für Wirtschaftswissenschaften - Leibniz-Informationszentrum Wirtschaft. If you have any questions about the object, please contact the data provider.
Show original at data provider

Object type

  • Konferenzbeitrag

Associated

  • Bertsche, Dominik
  • Brüggemann, Ralf
  • Kascha, Christian
  • ZBW - Leibniz-Informationszentrum Wirtschaft

Time of origin

  • 2019

Other Objects (12)

Directed Graphs and Variable Selection in Large Vector Autoregressive Models

Directed Graphs and Variable Selection in Large Vector Autoregressive Models

Directed graphs and variable selection in large vector autoregressive models

Artikel

Directed graphs and variable selection in large vector autoregressive models

Model Selection Methods for Panel Vector Autoregressive Models

Model Selection Methods for Panel Vector Autoregressive Models

Vector Autoregressive Analysis

Vector Autoregressive Analysis

Vector autoregressive analysis

Arbeitspapier

Vector autoregressive analysis

Generalized binary vector autoregressive processes

Generalized binary vector autoregressive processes

Stationary threshold vector autoregressive models

Artikel

Stationary threshold vector autoregressive models

Generalized binary vector autoregressive processes

Artikel

Generalized binary vector autoregressive processes

Bootstrap Autoregressive Order Selection

Bootstrap Autoregressive Order Selection

Bootstrap Autoregressive Order Selection

Bootstrap Autoregressive Order Selection

Structural vector autoregressive models with more shocks than variables identified via heteroskedasticity

Structural vector autoregressive models with more shocks than variables identified via heteroskedasticity

Structural vector autoregressive models with more shocks than variables identified via heteroskedasticity

Arbeitspapier

Structural vector autoregressive models with more shocks than variables identified via heteroskedasticity

Related objects