Forecasting economic policy uncertainty of BRIC countries using Bayesian VARs

Abstract

This paper utilizes the recently developed methods of compressing the parameters and the data for a high-dimensional vector autoregression (VAR) to forecast economic policy uncertainty (EPU) of Brazil, China, India and Russia (BRIC) based on EPUs of additional 18 other developed and developing countries. In line with the recent literature on spillover of EPUs across countries, we show that incorporating information of EPUs of other countries does indeed produce gains in forecasting the EPU of the BRIC bloc, irrespective of whether we compress the parameters or the data.

On the Exchange Rates Volatility and Economic Policy Uncertainty Nexus: A Panel VAR Approach for Emerging Markets

“…Specifically, we check if our results are altered if we (i) re-estimate IRFs based on an alternative lag structure, (ii) use the Global EPU (GEPU) index as an alternative proxy of the foreign EPU 17 and (iii) cut Singapore and China out of our sample since they have adopted different exchange regimes compared to the other countries 18 . Our sensitivity findings confirm that the overall dynamics of our PVAR are immune to all modifications 19 . Therefore, we interestingly provide strong and robust evidence.…”

“…Our finding is closely related toGupta and Sun (2020) which show for the BRIC that models including foreign EPU provide better forecasts than those with domestic EPU alone 17. This variable enters the PVAR system in logarithmic form and it is stationary in level (see Table1) provides more details on the panel unit root result 18.…”

“…According to the IMF (2018), the former (latter) adopt a soft pegged regime (managed floating) regime. The remaining countries adopt floating regimes 19. The sensitivity analysis results are detailed in Appendix B.…”

Analyzing the Impact of Brexit on Global Uncertainty Using Functional Linear Regression With Point of Impact: The Role of Currency and Equity Markets

“…Uncertainty is a latent variable, and hence one requires ways to measure it. In this regard, besides the various alternative metrics of uncertainty associated with financial markets (such as the implied-volatility indices (popularly called the VIX), realized volatility, idiosyncratic volatility of equity returns, corporate spreads), there are primarily three broad approaches to quantify uncertainty (Gupta and Sun, 2020;Bilgin et al, 2019): (1) A news-based approach, with the main idea behind this method being to perform searches of major newspapers for terms related to economic and policy uncertainty, and then to use the results to construct indices of uncertainty;…”

Point and density forecasting of macroeconomic and financial uncertainties of the USA

“…Given this, a pertinent question for policymakers is to determine the possible factors that can drive uncertainty, since forecasting the path of uncertainty would allow policy authorities to determine in which direction the macroeconomy and financial markets are headed, and accordingly decide on the appropriate policy response. However, despite the importance of the issue of accurately forecasting uncertainty, this literature is, to the best of our knowledge, restricted to only three papers, namely Wang, Zhang, Diao, and Wu (2015), Degiannakis and Filis (2019), and Gupta and Sun (2020). In the first paper, the authors successfully forecasted uncertainty of the USA using changes in prices of 23 commodities, especially when forecast combination methods were used.…”