Please use this identifier to cite or link to this item: https://hdl.handle.net/10419/312925 
Year of Publication: 
2025
Series/Report no.: 
Graduate Institute of International and Development Studies Working Paper No. HEIDWP06-2025
Publisher: 
Graduate Institute of International and Development Studies, Geneva
Abstract: 
This study investigates the application of Factor-Augmented Vector Autoregression (FAVAR) and Bayesian Vector Autoregression (BVAR) models for inflation forecasting. FAVAR models deal with high-dimensional data by extracting latent factors from extensive macroeconomic indicators, while BVAR models incorporate prior distributions to enhance forecast stability and precision in data-limited environments. Employing a comprehensive dataset of Uzbekistan-specific inflation determinants, we conduct an empirical assessment of both models, examining their predictive accuracy. Findings from this research aim to optimize inflation forecasting methodologies, providing the Central Bank of Uzbekistan with robust, data-driven insights for improved policy formulation.
Subjects: 
FAVAR
BVAR
inflation forecast
forecast combination
JEL: 
E30
E31
E37
Document Type: 
Working Paper

Files in This Item:
File
Size





Items in EconStor are protected by copyright, with all rights reserved, unless otherwise indicated.