Department of Economics and Business Economics

Vector Autoregressions with Parsimoniously Time Varying Parameters and an Application to Monetary Policy

Research output: Working paper/Preprint Working paperResearch

Standard

Vector Autoregressions with Parsimoniously Time Varying Parameters and an Application to Monetary Policy. / Callot, Laurent; Kristensen, Johannes Tang.

Aarhus : Institut for Økonomi, Aarhus Universitet, 2014.

Research output: Working paper/Preprint Working paperResearch

Harvard

APA

Callot, L., & Kristensen, J. T. (2014). Vector Autoregressions with Parsimoniously Time Varying Parameters and an Application to Monetary Policy. Institut for Økonomi, Aarhus Universitet. CREATES Research Papers No. 2014-41

CBE

MLA

Callot, Laurent and Johannes Tang Kristensen Vector Autoregressions with Parsimoniously Time Varying Parameters and an Application to Monetary Policy. Aarhus: Institut for Økonomi, Aarhus Universitet. (CREATES Research Papers; Journal number 2014-41). 2014., 31 p.

Vancouver

Author

Callot, Laurent ; Kristensen, Johannes Tang. / Vector Autoregressions with Parsimoniously Time Varying Parameters and an Application to Monetary Policy. Aarhus : Institut for Økonomi, Aarhus Universitet, 2014. (CREATES Research Papers; No. 2014-41).

Bibtex

@techreport{bbf5ddb8207e451eaa78b6cf97ee5d6a,
title = "Vector Autoregressions with Parsimoniously Time Varying Parameters and an Application to Monetary Policy",
abstract = "This paper studies vector autoregressive models with parsimoniously time-varying parameters. The parameters are assumed to follow parsimonious random walks, where parsimony stems from the assumption that increments to the parameters have a non-zero probability of being exactly equal to zero.We estimate the sparse and high-dimensional vector of changes to the parameters with the Lasso and the adaptive Lasso. The parsimonious random walk allows the parameters to be modelled non parametrically, so that our model can accommodate constant parameters, an unknown number of structural breaks, or parameters varying randomly.We characterize the finite sample properties of the Lasso by deriving upper bounds on the estimation and prediction errors that are valid with high probability, and provide asymptotic conditions under which these bounds tend to zero with probability tending to one.We also provide conditions under which the adaptive Lasso is able to achieve perfectmodel selection. We investigate by simulations the pproperties of the Lasso and the adaptive Lasso in settings where the parameters are stable, experience structural breaks, or follow a parsimonious randomwalk.We use our model to investigate the monetary policy response to inflation and business cycle fluctuations in the US by estimating a parsimoniously time varying parameter Taylor rule.We document substantial changes in the policy response of the Fed in the 1970s and 1980s, and since 2007, but also document the stability of this response in the rest of the sample.",
keywords = "Parsimony, time varying parameters, VAR, structural break, Lasso, Parsimony, Time varying parameters, VAR, Structural break, Lasso",
author = "Laurent Callot and Kristensen, {Johannes Tang}",
year = "2014",
language = "English",
series = "CREATES Research Papers",
publisher = "Institut for {\O}konomi, Aarhus Universitet",
number = "2014-41",
type = "WorkingPaper",
institution = "Institut for {\O}konomi, Aarhus Universitet",

}

RIS

TY - UNPB

T1 - Vector Autoregressions with Parsimoniously Time Varying Parameters and an Application to Monetary Policy

AU - Callot, Laurent

AU - Kristensen, Johannes Tang

PY - 2014

Y1 - 2014

N2 - This paper studies vector autoregressive models with parsimoniously time-varying parameters. The parameters are assumed to follow parsimonious random walks, where parsimony stems from the assumption that increments to the parameters have a non-zero probability of being exactly equal to zero.We estimate the sparse and high-dimensional vector of changes to the parameters with the Lasso and the adaptive Lasso. The parsimonious random walk allows the parameters to be modelled non parametrically, so that our model can accommodate constant parameters, an unknown number of structural breaks, or parameters varying randomly.We characterize the finite sample properties of the Lasso by deriving upper bounds on the estimation and prediction errors that are valid with high probability, and provide asymptotic conditions under which these bounds tend to zero with probability tending to one.We also provide conditions under which the adaptive Lasso is able to achieve perfectmodel selection. We investigate by simulations the pproperties of the Lasso and the adaptive Lasso in settings where the parameters are stable, experience structural breaks, or follow a parsimonious randomwalk.We use our model to investigate the monetary policy response to inflation and business cycle fluctuations in the US by estimating a parsimoniously time varying parameter Taylor rule.We document substantial changes in the policy response of the Fed in the 1970s and 1980s, and since 2007, but also document the stability of this response in the rest of the sample.

AB - This paper studies vector autoregressive models with parsimoniously time-varying parameters. The parameters are assumed to follow parsimonious random walks, where parsimony stems from the assumption that increments to the parameters have a non-zero probability of being exactly equal to zero.We estimate the sparse and high-dimensional vector of changes to the parameters with the Lasso and the adaptive Lasso. The parsimonious random walk allows the parameters to be modelled non parametrically, so that our model can accommodate constant parameters, an unknown number of structural breaks, or parameters varying randomly.We characterize the finite sample properties of the Lasso by deriving upper bounds on the estimation and prediction errors that are valid with high probability, and provide asymptotic conditions under which these bounds tend to zero with probability tending to one.We also provide conditions under which the adaptive Lasso is able to achieve perfectmodel selection. We investigate by simulations the pproperties of the Lasso and the adaptive Lasso in settings where the parameters are stable, experience structural breaks, or follow a parsimonious randomwalk.We use our model to investigate the monetary policy response to inflation and business cycle fluctuations in the US by estimating a parsimoniously time varying parameter Taylor rule.We document substantial changes in the policy response of the Fed in the 1970s and 1980s, and since 2007, but also document the stability of this response in the rest of the sample.

KW - Parsimony, time varying parameters, VAR, structural break, Lasso

KW - Parsimony

KW - Time varying parameters

KW - VAR

KW - Structural break

KW - Lasso

M3 - Working paper

T3 - CREATES Research Papers

BT - Vector Autoregressions with Parsimoniously Time Varying Parameters and an Application to Monetary Policy

PB - Institut for Økonomi, Aarhus Universitet

CY - Aarhus

ER -