Presentations - PhD students - EM - third year

Davide Bernardini

A 2-stage elastic net algorithm for estimation of sparse networks with heavy tailed data

Abstract

We propose a new 2-stage procedure that relies on the elastic net penalty to estimate a network based on partial correlations when data are heavy-tailed. The new estimator allows us to consider the lasso penalty as a special case. Using Monte Carlo simulations, we test the performance on several underlying network structures and four different multivariate distributions: Gaussian, t-Student with 3 and 20 degrees of freedom and contaminated Gaussian. Simulation analysis shows that the 2-stage estimator performs best for heavy-tailed data and it is also robust to distribution misspecification, both in terms of identification of the sparsity patterns and numerical accuracy. Empirical results on real-world data focus on the estimation of the European banking network during the Covid-19 pandemic. We show that the new estimator can provide interesting insights both for the development of network indicators, such as network strength, to identify crisis periods and for the detection of banking network properties, such as centrality and level of interconnectedness, that might play a relevant role in setting up adequate risk management and mitigation tools.

Mostafa Goudarzi

Tax evasion and shadow economy: An experimental study

Abstract

The purpose of this study is to investigate the tax evasion confronting expected utility theory and prospect theory. In a laboratory experiment, a credit market in the formal and shadow economies is simulated, with two different frames of supply and demand sides, allowing us to investigate experimentally the framing effect, reference point, and loss aversion on tax evasion behaviour. Furthermore, we investigate the role of semantic prosody in decision-making on involvement in the shadow economy to determine whether the concepts of prospect theory are reinforced or diminished by the effect of semantic prosody in the credit market. The final outcome of each choice in the experiment is fed into a lottery structure to be tested in the context of expected utility theory.

Blerita Korca

From voluntary to mandatory non-financial disclosure following Directive 2014/95/EU: an Italian case study

Abstract

This study investigates the non-financial disclosure in an Italian banking group following Directive 2014/95/EU over a period of eight years, from its voluntary (2013-2017) to mandatory (2018-2020) implementation. The paper relies both on primary and secondary data sources. It first adopts a content analysis on non-financial reports while considering other relevant available material. Second, the study relies upon semi-structured interviews and seminars to gather primary data. The analysis has been interpreted in light of institutional theory in order to understand the institutional forces driving non-financial disclosure. Results show that non-financial disclosure significantly increased in quantity after the regulation; however, the improvement in quality is fairly low, with the exception of themes relevant to the company under investigation. Through the lens of institutional theory, it emerges that an interplay of institutional mechanisms co-existed within the bank, during two periods of reporting for different topics of disclosure.

Keywords: Directive 2014/95/EU; regulation; non-financial disclosure; institutional theory; voluntary; mandatory

Vittorio Guida

Exploration and imitation: adaptive rationality and agent-based modelling.

Abstract

Exploration and exploitation studies on individuals have blossomed in the last two decades and inherited a large part of the excellent theoretical work produced by scholars as J. March. The literature appears to be very dense and vast, to the point that it may be difficult to have a comprehensive understanding of its valuable lessons. To the detection of this inner complexity of the literature, this study addresses what appears to be a void in it: the apparent scarcity of studies of individual imitation in the exploration and exploitation framework.
At the core of this paper there is an exploratory agent-based model designed to pursue a two-fold goal: offer a quantified visual representation of the theoretical models at work and produce preliminary insight for a future laboratory experiment to investigate imitation, exploration and exploitation.
Finally, by the means of simulated data, it is showed that learning through imitationstrongly depends on the interaction between those who imitate and those who are imitated. In particular, and as a proof of concept, a low number of targets (explorers) of possible imitative attempts makes imitation poorly useful in static environments as previously claimed by the literature.