Stochastic Model Specification Search for Time-Varying Parameter VARs

35 Pages Posted: 6 Mar 2014 Last revised: 7 Mar 2014

See all articles by Eric Eisenstat

Eric Eisenstat

University of Bucharest

Joshua C. C. Chan

University of Technology Sydney (UTS) - UTS Business School; Purdue University

Rodney W. Strachan

University of Queensland - School of Economics

Date Written: March 1, 2014

Abstract

This article develops a new econometric methodology for performing stochastic model specification search (SMSS) in the vast model space of time-varying parameter VARs with stochastic volatility and correlated state transitions. This is motivated by the concern of over-fitting and the typically imprecise inference in these highly parameterized models. For each VAR coefficient, this new method automatically decides whether it is constant or time-varying. Moreover, it can be used to shrink an otherwise unrestricted time-varying parameter VAR to a stationary VAR, thus providing an easy way to (probabilistically) impose stationarity in time-varying parameter models. We demonstrate the effectiveness of the approach with a topical application, where we investigate the dynamic effects of structural shocks in government spending on U.S. taxes and GDP during a period of very low interest rates.

Keywords: Bayesian Lasso, shrinkage, fiscal policy

JEL Classification: C11, C52, E37, E47

Suggested Citation

Eisenstat, Eric and Chan, Joshua C. C. and Strachan, Rodney W., Stochastic Model Specification Search for Time-Varying Parameter VARs (March 1, 2014). CAMA Working Paper No. 23/2014, Available at SSRN: https://ssrn.com/abstract=2403560 or http://dx.doi.org/10.2139/ssrn.2403560

Eric Eisenstat

University of Bucharest ( email )

14 Academiei St.
Bucharest, Bucuresti 70109
Romania

Joshua C. C. Chan (Contact Author)

University of Technology Sydney (UTS) - UTS Business School ( email )

Sydney
Australia

Purdue University

West Lafayette, IN 47907-1310
United States

Rodney W. Strachan

University of Queensland - School of Economics ( email )

Brisbane, QLD 4072
Australia

Here is the Coronavirus
related research on SSRN

Paper statistics

Downloads
55
Abstract Views
585
rank
416,161
PlumX Metrics