The Macroeconomic Impact of Jair Bolsonaro: A Synthetic Control Approach

Dissertation presented as the partial requirement for obtaining a Master's degree in Information Management, specialization in Knowledge Management and Business Intelligence This thesis aims to estimate the macroeconomic impact of the policies and actions of Brazilian President Jair Bolsonaro on the country's Gross Domestic Product (GDP) using the synthetic control method (SCM) developed by Abadie et al. (2003). This methodology is a powerful tool for causal inference as it allows for the estimation of a counterfactual outcome of a treatment group (in this case, Brazil under Bolsonaro) by constructing a synthetic control group that mimics the pre-treatment trends of the treatment group. The study finds that for the second part of the 2010 decade, the real outcome variable couldn't be replicated by the synthetic control. This suggests that there may have been unique factors at play in the Brazilian economy during this time that were not present in the donor pool and therefore couldn't be fully captured by the model. The study also finds that the recovery of the pandemic downturn in GDP was steeper for the synthetic Brazil compared to the real one. This could be somewhat related to how Bolsonaro handled it. However, despite the statistical significance of the results, it is not clear that the model can give us great insights in what it comes to have an answer to our research question – to give us a concrete answer to the question of how Brazil would have performed without Bolsonaro, further research may be needed.