How Regional Business Cycles Diffuse through Space and Time Evidence from Spatial Markov Model of Polish NUTS-3 Regions
DOI:
https://doi.org/10.24425/cejeme.2023.149072Keywords:
business cycle, spatial autoregression, NUTS-3, Markov switchingAbstract
In a national economy, are individual subnational regions business cycle
takers or setters? We address this important regional policy question by
investigating regional business cycles at NUTS-3 granularity in Poland (N = 73),
using two metrics in parallel: GDP dynamics and unemployment. To extract
the business cycle, we use a spatial Markov switching model that features both
idiosyncratic business cycle fluctuations across regions (as a 2-state chain), as
well as spatial interactions with other regions (as spatial autoregression). The
posterior distribution of the parameters is simulated with a Metropolis-withinGibbs procedure. We find a clear division into business cycle setters and takers,
the latter being largely (but not only) non-metropolitan regions.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Agnieszka Rabiej, Dominika Sikora-Kruszka, Andrzej Torój

This work is licensed under a Creative Commons Attribution 4.0 International License.