arXiv subjects

Marco Letta

Publications and source records attributed to Marco Letta.

4 recordsLinked to original sources

arXiv2024

On the (Mis)Use of Machine Learning with Panel Data

We provide the first systematic assessment of data leakage issues in the use of machine learning on panel data. Our organizing framework clarifies why neglecting the cross-sectional and longitudinal structure of these data leads to hard-to-detect data leakage, inflated out-of-sample performance, and an inadvertent overestimation of the real-world usefulness and applicability of machine learning models. We then offer empirical guidelines for practitioners to ensure the correct implementation of supervised machine learning in panel data environments. An empirical application, using data from over 3,000 U.S. counties spanning 2000-2019 and focused on income prediction, illustrates the practical relevance of these points across nearly 500 models for both classification and regression tasks.

econ.EM↗

arXiv2024

Climate Immobility Traps: A Household-Level Test

The complex relationship between climate shocks, migration, and adaptation hampers a rigorous understanding of the heterogeneous mobility outcomes of farm households exposed to climate risk. To unpack this heterogeneity, the analysis combines longitudinal multi-topic household survey data from Nigeria with a causal machine learning approach, tailored to a conceptual framework bridging economic migration theory and the poverty traps literature. The results show that pre-shock asset levels, in situ adaptive capacity, and cumulative shock exposure drive not just the magnitude but also the sign of the impact of agriculture-relevant weather anomalies on the mobility outcomes of farming households. While local adaptation acts as a substitute for migration, the roles played by wealth constraints and repeated shock exposure suggest the presence of climate-induced immobility traps.

econ.GN↗

arXiv2023

Causal inference and policy evaluation without a control group

Without a control group, the most widespread methodologies for estimating causal effects cannot be applied. To fill this gap, we propose the Machine Learning Control Method, a new approach for causal panel analysis that estimates causal parameters without relying on untreated units. We formalize identification within the potential outcomes framework and then provide estimation based on machine learning algorithms. To illustrate the practical relevance of our method, we present simulation evidence, a replication study, and an empirical application on the impact of the COVID-19 crisis on educational inequality. We implement the proposed approach in the companion R package MachineControl

econ.EM↗

arXiv2021

Was there a COVID-19 harvesting effect in Northern Italy?

We investigate the possibility of a harvesting effect, i.e. a temporary forward shift in mortality, associated with the COVID-19 pandemic by looking at the excess mortality trends of an area that registered one of the highest death tolls in the world during the first wave, Northern Italy. We do not find any evidence of a sizable COVID-19 harvesting effect, neither in the summer months after the slowdown of the first wave nor at the beginning of the second wave. According to our estimates, only a minor share of the total excess deaths detected in Northern Italian municipalities over the entire period under scrutiny (February - November 2020) can be attributed to an anticipatory role of COVID-19. A slightly higher share is detected for the most severely affected areas (the provinces of Bergamo and Brescia, in particular), but even in these territories, the harvesting effect can only account for less than 20% of excess deaths. Furthermore, the lower mortality rates observed in these areas at the beginning of the second wave may be due to several factors other than a harvesting effect, including behavioral change and some degree of temporary herd immunity. The very limited presence of short-run mortality displacement restates the case for containment policies aimed at minimizing the health impacts of the pandemic.

econ.GN↗