Empirical validation of agent-based models

Thomas Lux*, Remco C.J. Zwinkels

*Corresponding author for this work

Research output: Chapter in Book / Report / Conference proceedingChapterAcademicpeer-review

650 Downloads (Pure)


The literature on agent-based models has been highly successful in replicating many stylized facts of financial and macroeconomic time series. Over the past decade, however, also advances in the estimation of such models have been made. Due to the inherent heterogeneity of agents and nonlinearity of agent-based models, fundamental choices have to be made to take the models to the data. In this chapter we provide an overview of the current literature on the empirical validation of agent-based models. We discuss potential lessons from other fields of applications of agent-based models, avenues for estimation of reduced form and 'full-fledged' agent-based models, estimation methods, as well as applications and results.

Original languageEnglish
Title of host publicationHandbook of Computational Economics
Subtitle of host publicationVolume 4: Heterogeneous agent modeling
EditorsCars Hommes, Blake LeBaron
Number of pages52
ISBN (Electronic)9780444641328
ISBN (Print)9780444641311
Publication statusPublished - 2018

Publication series

NameHandbook of Computational Economics
ISSN (Print)1574-0021


  • Agent-based models
  • Method of moments
  • Reduced form models
  • Sequential Monte Carlo
  • State space models
  • Switching mechanisms
  • Validation

Cite this