Quantifying uncertainty in economics policy predictions: A Bayesian & Monte Carlo based data-driven approach

Shafeeq Ur Rahaman and Mahe Jabeen Abdul

International Review of Financial Analysis, 2025, vol. 102, issue C

Abstract: Economic policy uncertainty relates to the unpredictability in government policies that can impact economic decision-making. High policy uncertainty can lead to less investment, slower economic growth, and increased volatility in financial markets. In this study, Markov Chain Monte Carlo (MCMC) simulations and Bayesian Hierarchical Modeling (BHM) are employed to quantify policy prediction uncertainty. This research focuses essentially on key policy domains and macroeconomic tools where uncertainty underlies crucial influences upon economic decisions. The methodology integrates data collection, feature scaling, normalization, Bayesian inference using MCMC simulations, uncertainty quantification and policy prediction to produce predictive insights under various economic scenarios. The Bayesian Hierarchical Model was employed to estimate the relationships between macroeconomic variables and policy outcomes. The posterior distribution results revealed significant predictors, with certain factors like monetary policy uncertainty exerting a substantial negative impact, while others such as equity market-related uncertainty showed positive influence. A rigorous uncertainty quantification step provided credible intervals for predicted outcomes with a 95 % credible interval ranging between 0.276 and 0.359. This enabled an assessment of the potential variability in predictions based on differing levels of economic uncertainty. The study concluded with policy predictions generated under two distinct economic scenarios. Under conditions of high uncertainty during global economic crisis, the predicted policy outcome was −0.2346, while a moderate uncertainty scenario during typical economic fluctuations resulted in a less negative outcome of −0.2060. These results demonstrate the sensitivity of economic policy predictions to varying levels of uncertainty. The findings provide a robust framework for understanding and quantifying uncertainty in economic policy-making. By applying BHM and Monte Carlo methods, this study can help in the establishment of more flexible and adaptive economic strategies in the face of uncertainty.

Keywords: Economic policy uncertainty; Predictive modeling Markov Chain Monte Carlo algorithm; Bayesian statistics; Computational economics (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S1057521925002443
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:finana:v:102:y:2025:i:c:s1057521925002443

DOI: 10.1016/j.irfa.2025.104157

Access Statistics for this article

International Review of Financial Analysis is currently edited by B.M. Lucey

More articles in International Review of Financial Analysis from Elsevier
Bibliographic data for series maintained by Catherine Liu ().