Bayesian Estimation of Economic Simulation Models Using Neural Networks
Author:
Open Access
- 22 February 2021
- journal article
- research article
- Published by Springer Nature in Computational Economics
- Vol. 59 (2) , 599-650
Abstract
Recent advances in computing power and the potential to make more realistic assumptions due to increased flexibility have led to the increased prevalence of simulation models in economics. While models of this class, and particularly agent-based models, are able to replicate a number of empirically-observed stylised facts not easily recovered by more traditional alternatives, such models remain notoriously difficult to estimate due to their lack of tractable likelihood functions. While the estimation literature continues to grow, existing attempts have approached the problem primarily from a frequentist perspective, with the Bayesian estimation literature remaining comparatively less developed. For this reason, we introduce a widely-applicable Bayesian estimation protocol that makes use of deep neural networks to construct an approximation to the likelihood, which we then benchmark against a prominent alternative from the existing literature. Overall, we find that our proposed methodology consistently results in more accurate estimates in a variety of settings, including the estimation of financial heterogeneous agent models and the identification of changes in dynamics occurring in models incorporating structural breaks.Keywords
Funding Information
- Commonwealth Scholarship Commission (Not applicable)
This publication has 48 references indexed in Scilit:
- Credit Money and Macroeconomic Instability in the Agent-based Model and Simulator EuraceEconomics, 2010
- Tutorial on agent-based modelling and simulationJournal of Simulation, 2010
- Applying the method of simulated moments to estimate a small agent-based asset pricing modelJournal of Empirical Finance, 2009
- The economy needs agent-based modellingNature, 2009
- The virtues and vices of equilibrium and the future of financial economicsComplexity, 2008
- Empirical validation of stochastic models of interacting agentsThe European Physical Journal B, 2006
- GPU implementation of neural networksPattern Recognition, 2004
- The context-tree weighting method: basic propertiesIEEE Transactions on Information Theory, 1995
- A Method of Simulated Moments for Estimation of Discrete Response Models Without Numerical IntegrationEconometrica, 1989
- Multilayer feedforward networks are universal approximatorsNeural Networks, 1989