Dottoressa di ricerca

ciclo: XXXV

Titolo della tesi: Sustainable Economic Growth: Renweable Energies, Emissions and Climate change

The first part of this thesis compares the predictive power of different models to forecast the real U.S. GDP. Using quarterly data from 1976 to 2020, we find that the machine learning K-Nearest Neighbor (KNN) model captures the self-predictive ability of the U.S. GDP and performs better than traditional time series analysis. We explore the inclusion of predictors such as the yield curve, its latent factors, and a set of macroeconomic variables in order to increase the level of forecasting accuracy. The predictions result to be improved only when considering long forecast horizons. The use of machine learning algorithm provides additional guidance for data-driven decision making. The economic growth is a fundamental measure/indicator of a country but nowadays it is mandatory to do a shift towards a sustainable economic growth, facing the environmental challenges that include climate change and CO2 emissions. Indeed, in the second part of the work, the interactions among climatic factors, renewable energy production, emissions and economic growth, both at the country and the cross-country level, are assessed using a Matrix AutoRegressive (MAR) model. The analysis considers matrix variate time series of European countries belonging to the G7 (EU27) from 1980 to 2020. At the macro level, the findings show i) a recovery capacity of the economy from past shocks, ii) a negative effect of renewable energies on economic growth due to fixed technological costs in the short term and iii) a beneficial effect of such energies in lowering the emissions. The study of the interactions across countries shows that the aggregate indicators of Germany and France have a positive impact on climatic and economic factors of the other G7 (EU27) members, possibly due to their environmental commitment. Furthermore, the impulse response functions reveal that a shock in the precipitation and wind speed of Germany is beneficial for the economic growth of the G7 (EU27) in the short term whereas a shock in solar radiation has a negative effect on the economic growth. Finally, the Network Estimation for Time Series (NETS) is proposed as new methodological approach estimation for the MAR.

Produzione scientifica

11573/1615109 - 2021 - GDP Forecasting: Machine Learning, Linear or Autoregression?
Maccarrone, Giovanni; Morelli, Giacomo; Spadaccini, Sara - 01a Articolo in rivista
rivista: FRONTIERS IN ARTIFICIAL INTELLIGENCE ([Lausanne]: Frontiers Media S.A., [2018]-) pp. - - issn: 2624-8212 - wos: WOS:000751704800164 (0) - scopus: 2-s2.0-85117939202 (1)

11573/1654920 - 2021 - Retrospective Survey of Treatment and Outcomes of COVID-19 in the community
Willcox, Merlin; Graz, Bertrand; Houriet, Joelle; Becque, Taeko; Leonti, Marco; Francis, Nick; Mollica, Cristina; Spadaccini, Sara - 01h Abstract in rivista
rivista: EUROPEAN JOURNAL OF INTEGRATIVE MEDICINE (Amsterdam ; Munich : Elsevier) pp. - - issn: 1876-3820 - wos: (0) - scopus: (0)

¬© Università degli Studi di Roma "La Sapienza" - Piazzale Aldo Moro 5, 00185 Roma