Ortiz Gimenez, Victor (2024) Brexit, Trade Disruptions, and Export Recommendations. Advisor: Riccaboni, Prof. Massimo. Coadvisor: Serti, Prof. Francesco . pp. 136. [IMT PhD Thesis]
![[img]](http://e-theses.imtlucca.it/style/images/fileicons/text.png) |
Text (Doctoral thesis)
Thesis_Victor_OrtizGimenez_final (1).pdf - Published Version Restricted to IMT staff and National library only until 31 October 2025. Available under License Creative Commons Attribution Non-commercial Share Alike. Download (1MB) | Request a copy |
Abstract
This doctoral dissertation is structured into three chapters, each ad- dressing aspects related to policy evaluation, with a focus on events car- rying substantial implications for the economy and international trade. These events include the Brexit referendum, trade disruptions, and the development of export recommendations. The Economic Cost of a Referendum. The Case of Brexit. This paper esti- mates how GDP would have behaved in the United Kingdom after the Brexit referendum in the absence of the mentioned poll using the Syn- thetic Control Method. We contribute to the research on the effects of Brexit by quantifying the macroeconomic cost of this referendum before the actual Brexit has taken place. We find a large and significant negative effect of the Brexit referendum on the GDP of UK. This loss is increasing in time representing, in 2017 Q4, 1.71% of the observed GDP of UK. Assessing the Heterogeneous Impact of Economy-Wide Shocks: A Machine Learning Approach Applied to Colombian Firms. This paper investigates the impact of COVID-19 on Colombian exports, revealing a substantial de- cline in survival probabilities during 2020. On average, we find that the COVID-19 shock decreased a firm’s probability of surviving in the export market by about 20 percentage points in April 2020. Importantly, ex- porters more integrated into Global Value Chains (GVCs) and importing higher value emerged as pivotal in bolstering exporter resilience during the crisis, emphasizing the need for policies supporting varied import networks, as well as international trade facilitation. Methodologically, this research innovates by utilizing causal Machine Learning (ML) tools in scenarios where the pervasive nature of the shock hinders the identi- fication of a control group unaffected by the shock, as well as the ex-ante definition of the intensity of the shock’s exposure of each unit, making a traditional control group identification unfeasible. This approach effec- tively predicts firms’ trade and uses these predictions to reconstruct the counterfactual distribution of firms’ trade under different scenarios and to study treatment effect heterogeneity. Exports’ Survival in New Markets: A firm-level export recommendation model. This paper investigates the factors that better predict a firm’s trade status of exporters after expanding to a new destination, specif- ically whether they continue exporting after two years. Using Colom- bian customs data, I show that market-level information is crucial for understanding export survival rates, beyond traditional firm-level char- acteristics like export experience. The paper introduces a novel Machine Learning-based export market entry recommendation tool, designed at the firm-product market level. While firms in the sample did not have access to this tool, the analysis observes which firms chose new destina- tions that align with the recommendations generated by the tool. Sim- ulated back-testing indicates that firms selecting destinations consistent with the tool’s guidance would have experienced a 5 percentage point higher survival rate compared to those choosing other destinations. Ad- ditionally, product growth would have been 34 percentage points higher for products where at least one firm followed the tool’s suggested market entry, compared to those that did not. The findings suggest that incom- plete market insights may lead to sub-optimal export decisions and that exporters incur temporary trade as a way of experimentation and to re- solve incomplete market information.
| Item Type: | IMT PhD Thesis |
|---|---|
| Subjects: | H Social Sciences > HB Economic Theory |
| PhD Course: | Economics, Networks and Business Analytics |
| Identification Number: | https://doi.org/10.13118/imtlucca/e-theses/431 |
| Date Deposited: | 24 Oct 2024 10:31 |
| URI: | http://e-theses.imtlucca.it/id/eprint/431 |
Actions (login required, only for staff repository)
 |
View Item |
