A Dynamic Factor and Neural Networks Analysis of the Co-movement of Public Revenues in the EMU

Abstract

This paper shows that the co-movement of public revenues in the European Monetary Union (EMU) is driven by an unobserved common factor. Our empirical analysis uses yearly data covering the period 1970–2014 for 12 selected EMU member countries. We have found that this common component has a significant impact on public revenues in the majority of the countries. We highlight this common pattern in a dynamic factor model (DFM). Since this factor is unobservable, it is difficult to agree on what it represents. We argue that the latent factor that emerges from the two different empirical approaches used might have a composite nature, being the result of both the more general convergence of the economic cycles of the countries in the area and the increasingly better tuned tax structure. However, the original aspect of our paper is the use of a back-propagation neural networks (BPNN)-DF model to test the results of the time-series. At the level of computer programming, the results obtained represent the first empirical demonstration of the latent factor’s presence.

Do gasoline and diesel prices co-move? Evidence from the time–frequency domain

“…Future research may investigate the co-movements between gasoline and diesel prices using ML or artificial neural networks analysis to shed further light on the unobserved common component (Magazzino and Mele 2021 ).…”

Innovation, income, and waste disposal operations in Korea: evidence from a spectral granger causality analysis and artificial neural networks experiments

“…ANNs receive external signals on a layer of input nodes (processing units), each of which is connected with an intermediate layer of internal nodes, possibly even organized on several levels. Each node processes the incoming signals received and transmits the result to the nodes of the next layer (Magazzino & Mele, 2021;Magazzino et al, 2021a, b, c, d, e;Mele & Magazzino, 2020;Mele et al, 2021a, b). The fundamental element is the neuron: it is nothing more than a mathematical model that receives inputs and, through an appropriate calculation process, generates an output (Fig.…”

Fiscal sustainability in the GCC countries

“…This creates a link between the sustainability of the public budget and the so-called "fiscal or budgetary space", which means the room for maneuver for fiscal stimulus policies, without risking an unsustainable debt spiral. The fiscal space is particularly limited for countries participating in a monetary union: in fact, the risk of insolvency depends on the level of interest rates on the debt, which modifies the interest expenditure curve [40]. De Grauwe [16] considered the fact that this phenomenon can open the door to self-fulfilling crises.…”

“…Future research might analyze the fiscal solvency of this area using different empirical methodologies, such as machine learning (ML) or artificial neural networks (ANNs) [40]. you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made.…”