17

Macroeconometric Modeling for Policy

Gunnar Bårdsen and Ragnar Nymoen

Abstract

The first part of this chapter sets out a coherent approach to dynamic macroeconometric model-
building; the second part demonstrates the approach through building and evaluating a small
econometric model; the final part demonstrates various usages of the model for policy.

17.1 Introduction 852
17.2 A modeling framework 856
17.2.1 Linearization 857
17.2.2 Discretization 858
17.2.3 Equilibrium correction representations and cointegration 859
17.2.4 System representations 860
17.2.5 From a discretized and linearized cointegrated VAR representation to a
dynamic SEM in three steps 861
17.2.5.1 First step: the statistical system 861
17.2.5.2 Second step: the overidentified steady state 862
17.2.5.3 Third step: the dynamic SEM 863
17.2.6 Example: the supply side of a medium-term macroeconomic
model 863
17.2.6.1 Economic theory 863
17.2.6.2 Cointegration and long-run identification 867
17.2.6.3 VAR and identified equilibrium correction system 868
17.2.6.4 Economic interpretation of the steady state 870
17.2.6.5 Implementation in the Norwegian aggregate model 874
17.3 Building a model for monetary policy analysis 874
17.3.1 The model and its transmission mechanisms 875
17.3.2 Steady state 879
17.3.3 Stability of the steady state 882
17.4 Macroeconometric models as tools for policy analysis 883
17.4.1 Tractability: stylized representations 884
17.4.2 Shock analysis: dynamic simulations 887
17.4.2.1 How strong is the policy instrument? 887
17.4.2.2 Fitting the facts 888
17.4.2.3 Shock analysis with dynamic multipliers 888

851