The presence of a latent factor in gasoline and diesel prices co-movements

Cosimo Magazzino, Marco Mele, Claudiu Tiberiu Albulescu, Nicholas Apergis () and Mihai Ioan Mutascu
Additional contact information
Mihai Ioan Mutascu: LEO - Laboratoire d'Économie d'Orleans [2022-...] - UO - Université d'Orléans - UT - Université de Tours - UCA - Université Clermont Auvergne

Post-Print from HAL

Abstract: Abstract This paper proposes a novel approach to identify the presence of a latent factor in the co-movements of gasoline and diesel prices in the three major European Union economies, (France, Germany, and Italy) using daily data from January 3, 2005, to June 28, 2021. More precisely, we advance an artificial neural networks algorithm estimated through a machine learning experiment through the backpropagation system to show that the neural signal is altered by an element that could coincide with a latent factor in the fuel price co-movements. We consider the role of the fuel tax systems and the connection between gasoline and diesel prices in these countries. The estimations indicate the presence of an unobservable component (the latent factor) in the fuel price co-movements, capable of influencing NN. This result validates the previous findings reported in the literature, indicating an excess co-movement in fuel prices. It also has implications in terms of fuel price forecasts in the short run.

Date: 2024-03-05
References: Add references at CitEc
Citations:

Published in Empirical Economics, 2024, 66 (5), pp.1921-1939. ⟨10.1007/s00181-023-02523-6⟩

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
Journal Article: The presence of a latent factor in gasoline and diesel prices co-movements (2024)
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:hal:journl:hal-04802059

DOI: 10.1007/s00181-023-02523-6

Access Statistics for this paper

More papers in Post-Print from HAL
Bibliographic data for series maintained by CCSD ().