Logo Logo
Hilfe
Hilfe
Switch Language to English

De Pretis, Francesco ORCID logoORCID: https://orcid.org/0000-0001-8395-7833; Glielmo, Aldo ORCID logoORCID: https://orcid.org/0000-0002-4737-2878 und Landes, Jürgen ORCID logoORCID: https://orcid.org/0000-0003-3105-6624 (Mai 2025): Assessing inference to the best explanation posteriors for the estimation of economic agent-based models. In: International Journal of Approximate Reasoning, Bd. 180, 109388 [PDF, 2MB]

Abstract

Explanatory relationships between data and hypotheses have been suggested to play a role in the formation of posterior probabilities. This suggestion was tested in a toy environment and supported by simulations by David H. Glass. We here put forward a variety of inference to the best explanation approaches for determining posterior probabilities by intertwining Bayesian and inference to the best explanation approaches. We then simulate their performances for the estimation of parameters in the Brock and Hommes agent-based model for asset pricing in finance. We find that performances depend on circumstances and also on the evaluation metric. However, most of the time our suggested approaches outperform the Bayesian approach.

Dokument bearbeiten Dokument bearbeiten