Forecast Sensitivity to Global Risks : A BVAR Analysis

Developing countries face uncertainties driven by global macroeconomic variables over which they have little to no control. Key exogenous factors faced by most developing countries include interest rates in high-income countries, commodity prices, global demand for exports, and remit- tance inflows. While these variables are sensitive to common global shocks, they also exhibit idiosyncratic fluctuations. This paper employs a Bayesian Vector Autoregression model to capture interdependencies of global variables and simulates global risks using the empirical joint distribution of global shock as captured by joint Bayesian Vector Autoregression errors. The simulated shocks are then integrated into the World Bank’s macro-structural model to assess how a range of potential global disturbances could impact economic outcomes across countries. The methodology is applied to 115 countries, using the World Bank’s fall 2024 edition of the Macro-Poverty Outlook forecasts as a baseline. Although the individual country results are heterogeneous, the aggregate distribution of gross domestic product outcomes across the 115 countries suggests that global factors influence gross domestic product levels in individual developing countries by less than plus or minus 2 percent in most years, but by between 2 and 4 percent in about 3 in 10 years.