### Abstract

Language | English |
---|---|

Pages | 33-56 |

Number of pages | 24 |

Journal | Review of Economic Analysis |

Volume | 9 |

Publication status | Published - 9 Apr 2017 |

### Fingerprint

### Keywords

- multivariate time series
- vector autoregression
- state space model
- Bayesian
- single-equation models
- multiple equation models
- empirical macroeconomics
- Big Data

### Cite this

}

*Review of Economic Analysis*, vol. 9, pp. 33-56.

**Bayesian methods for empirical macroeconomics with big data.** / Koop, Gary.

Research output: Contribution to journal › Article

TY - JOUR

T1 - Bayesian methods for empirical macroeconomics with big data

AU - Koop, Gary

PY - 2017/4/9

Y1 - 2017/4/9

N2 - Bayesian econometric methods are increasingly popular in empirical macroeconomics. They have been particularly popular among macroeconomists working with Big Data (where the number of variables under study is large relative to the number of observations). This paper, which is based on a keynote address at the Rimini Centre for Economic Analysisí2016 Money-Macro-Finance Workshop, explains why this is so. It discusses the problems that arise with conventional econometric methods and how Bayesian methods can successfully overcome them either through use of prior shrinkage or through model averaging. The discussion is kept at a relatively non-technical level, providing the main ideas underlying and motivation for the models and methods used. It begins with single-equation models (such as regression) with many explanatory variables, then moves on to multiple equation models (such as Vector Autoregressive, VAR, models) before tacking the challenge caused by parameter change (e.g. changes in VAR coe¢ cients or volatility). It concludes with an example of how the Bayesian can address all these challenges in a large multi-country VAR involving 133 variables: 7 variables for each of 19 countries.

AB - Bayesian econometric methods are increasingly popular in empirical macroeconomics. They have been particularly popular among macroeconomists working with Big Data (where the number of variables under study is large relative to the number of observations). This paper, which is based on a keynote address at the Rimini Centre for Economic Analysisí2016 Money-Macro-Finance Workshop, explains why this is so. It discusses the problems that arise with conventional econometric methods and how Bayesian methods can successfully overcome them either through use of prior shrinkage or through model averaging. The discussion is kept at a relatively non-technical level, providing the main ideas underlying and motivation for the models and methods used. It begins with single-equation models (such as regression) with many explanatory variables, then moves on to multiple equation models (such as Vector Autoregressive, VAR, models) before tacking the challenge caused by parameter change (e.g. changes in VAR coe¢ cients or volatility). It concludes with an example of how the Bayesian can address all these challenges in a large multi-country VAR involving 133 variables: 7 variables for each of 19 countries.

KW - multivariate time series

KW - vector autoregression

KW - state space model

KW - Bayesian

KW - single-equation models

KW - multiple equation models

KW - empirical macroeconomics

KW - Big Data

UR - http://www.rofea.org/

M3 - Article

VL - 9

SP - 33

EP - 56

JO - Review of Economic Analysis

T2 - Review of Economic Analysis

JF - Review of Economic Analysis

SN - 1973-3909

ER -