Using VARs and TVP-VARs with Many Macroeconomic Variables

Research output: Working paperDiscussion paper

Abstract

This paper discusses the challenges faced by the empirical macroeconomist and methods for surmounting them. These challenges arise due to the fact that macroeconometric models potentially include a large number of variables and allow for time variation in parameters. These considerations lead to models which have a large number of parameters to estimate relative to the number of observations. A wide range of approaches are surveyed which aim to overcome the resulting problems. We stress the related themes of prior shrinkage, model averaging and model selection. Subsequently, we consider a particular modelling approach in detail. This involves the use of dynamic model selection methods with large TVP-VARs. A forecasting exercise involving a large US macroeconomic data set illustrates the practicality and empirical success of our approach.
LanguageEnglish
Place of PublicationGlasgow
PublisherUniversity of Strathclyde
Pages1-34
Number of pages35
Volume13
Publication statusPublished - 14 Jan 2013

Fingerprint

Macroeconomic variables
Model selection
Modeling
Macroeconometric model
Macroeconomics
Model averaging
Shrinkage
Exercise
Time variation

Keywords

  • bayesian var
  • forecasting
  • time-varying coefficients
  • state-space model

Cite this

Koop, G. (2013). Using VARs and TVP-VARs with Many Macroeconomic Variables. (03 ed.) (pp. 1-34). Glasgow: University of Strathclyde.
Koop, Gary. / Using VARs and TVP-VARs with Many Macroeconomic Variables. 03. ed. Glasgow : University of Strathclyde, 2013. pp. 1-34
@techreport{eaca23aa3c4045a889e9625c31d54676,
title = "Using VARs and TVP-VARs with Many Macroeconomic Variables",
abstract = "This paper discusses the challenges faced by the empirical macroeconomist and methods for surmounting them. These challenges arise due to the fact that macroeconometric models potentially include a large number of variables and allow for time variation in parameters. These considerations lead to models which have a large number of parameters to estimate relative to the number of observations. A wide range of approaches are surveyed which aim to overcome the resulting problems. We stress the related themes of prior shrinkage, model averaging and model selection. Subsequently, we consider a particular modelling approach in detail. This involves the use of dynamic model selection methods with large TVP-VARs. A forecasting exercise involving a large US macroeconomic data set illustrates the practicality and empirical success of our approach.",
keywords = "bayesian var, forecasting, time-varying coefficients, state-space model",
author = "Gary Koop",
note = "Published as a paper within the Discussion Papers in Economics, No. 13-03 (2013)",
year = "2013",
month = "1",
day = "14",
language = "English",
volume = "13",
pages = "1--34",
publisher = "University of Strathclyde",
edition = "03",
type = "WorkingPaper",
institution = "University of Strathclyde",

}

Koop, G 2013 'Using VARs and TVP-VARs with Many Macroeconomic Variables' 03 edn, University of Strathclyde, Glasgow, pp. 1-34.

Using VARs and TVP-VARs with Many Macroeconomic Variables. / Koop, Gary.

03. ed. Glasgow : University of Strathclyde, 2013. p. 1-34.

Research output: Working paperDiscussion paper

TY - UNPB

T1 - Using VARs and TVP-VARs with Many Macroeconomic Variables

AU - Koop, Gary

N1 - Published as a paper within the Discussion Papers in Economics, No. 13-03 (2013)

PY - 2013/1/14

Y1 - 2013/1/14

N2 - This paper discusses the challenges faced by the empirical macroeconomist and methods for surmounting them. These challenges arise due to the fact that macroeconometric models potentially include a large number of variables and allow for time variation in parameters. These considerations lead to models which have a large number of parameters to estimate relative to the number of observations. A wide range of approaches are surveyed which aim to overcome the resulting problems. We stress the related themes of prior shrinkage, model averaging and model selection. Subsequently, we consider a particular modelling approach in detail. This involves the use of dynamic model selection methods with large TVP-VARs. A forecasting exercise involving a large US macroeconomic data set illustrates the practicality and empirical success of our approach.

AB - This paper discusses the challenges faced by the empirical macroeconomist and methods for surmounting them. These challenges arise due to the fact that macroeconometric models potentially include a large number of variables and allow for time variation in parameters. These considerations lead to models which have a large number of parameters to estimate relative to the number of observations. A wide range of approaches are surveyed which aim to overcome the resulting problems. We stress the related themes of prior shrinkage, model averaging and model selection. Subsequently, we consider a particular modelling approach in detail. This involves the use of dynamic model selection methods with large TVP-VARs. A forecasting exercise involving a large US macroeconomic data set illustrates the practicality and empirical success of our approach.

KW - bayesian var

KW - forecasting

KW - time-varying coefficients

KW - state-space model

M3 - Discussion paper

VL - 13

SP - 1

EP - 34

BT - Using VARs and TVP-VARs with Many Macroeconomic Variables

PB - University of Strathclyde

CY - Glasgow

ER -

Koop G. Using VARs and TVP-VARs with Many Macroeconomic Variables. 03 ed. Glasgow: University of Strathclyde. 2013 Jan 14, p. 1-34.