Séminaires de recherche

Confidence Region for long memory based on Inverting Bootstrap Tests: an application to Stock Market Indices

Mardi | 2018-06-26
Salle Sully 5 16h – 17h20

Christian DE PERETTI – Carole SIANI

In the context of long memory, the finite-sample distortion of statistic distributions is so large, that bootstrap confidence intervals (percentile and percentile-t) for the long memory parameter do not perform better than the corresponding asymptotic confidence interval. In this paper, we propose confidence intervals based on inverting bootstrap tests for the long memory parameter. Monte Carlo experiments are carried out for assessing the confidence intervals in finite sample for various situations. The results are graphically displayed using coverage plots and coverage-effectiveness curves for confidence regions. We show that classical confidence intervals (asymptotic as well as bootstrap) have very poor performances, whereas confidence intervals based on inverting bootstrap tests have quite satisfactory performance. These intervals are then applied on stock market indices.

On the consistency of the Z-score to measure the bank risk

Mardi | 2018-06-19
Salle des thèses 16h – 17h20


This paper raises questions about the consistency of the Z-score, which is the most applied accounting-based measure of bank risk in the banking literature. In spite of its advantage, namely the concept of risk on which it relies, the traditional formula is precisely inconsistent with its own concept. The Z-score is deduced from the probability that bank’s losses exceed its capital, but under the very unrealistic assumption of normally distributed returns on assets. We show that, because of this hypothesis, the traditional Z-score fails to consider correctly the distribution of banks’ returns. To make the Z-score consistent and preserve its original concept of risk, we propose more flexible distribution functions instead of normal distribution one. Between skew normal and stable distributions, we prove that the latter fits the best the distribution of banks’ returns and therefore provides more reliable results for the Z-score. An application on the experience of European banks confirms this assertion.

Constrained optimisation applied to Input/Output Table regionalisation with scarce data: application to La Réunion (France)

Mardi | 2018-06-12
Salle des thèses 16h – 17h20


Local data scarcity may lead Input-Output (I/O) analysts to build aggregated subnational models. Based on the case of the French economy, we claim that local I/O tables should instead be as detailed as the national ones. Any local data – never mind how aggregated – is more thoroughly used to adapt existing detailed national tables, than in an oversimplified model of the local economy. Using a deterministic approach based on industry output disaggregation and constrained optimisation, we successfully apply these recommendations to the construction of I/O tables for the French overseas department of La Réunion. Refining these tables by using a time series of economic accounts lead to mixed results. The overall model fitness to local accounts improved significantly, but at the expense of some instabilities in the I/O coefficient estimates. We explore several plausible explanations for these instabilities, and suggest that more refined probabilistic or Artificial Intelligence methods could alleviate them.

Structural Breaks and Herding Behaviour in Cryptocurrencies

Mardi | 2018-06-05
Salle des thèses 16h – 17h20

Dimitrios ASTERIOU – Kyriaki BEGIAZI

Blockchain technology created cryptocurrencies. In January 2018, Bitcoin gained attention, as the most known electronic currency with the highest capitalisation. This paper examines the characteristics of the main cryptocurrencies (Bitcoin, Ethereum, Ripple, Litecoin, Stellar, NEM, Dash, Monero, Tether) from August 2015 to February 2018. Cryptocurrency index reported a structural break on January 2018, according to Chow breakpoint test. While Bitcoin was already on a steady decline since reaching its all-time high valuation, the magnitude of the situation worsened on January 15, 2018, as other major cryptocurrencies like Bitcoin Cash, Ripple and Litecoin followed its lead. However, Bai-Perron multiple break point tests do not provide evidence of any breakpoints. Apart from documenting stability diagnostics, this study provides evidence for the existence of herding effects in the cryptocurrency market. However, Finally, asymmetric herding effects are not documented during the days of negative market returns.

Geographical economics and income Disparities across Colombian Departamentos: Analysis for the period 1990-2015

Mardi | 2018-05-29
Salle des thèses 16h – 17h20


This paper focuses on the analysis of the role played by market potential in the spatial income structure observed in Colombia over the period 1990-2015. Based on the geographical economics theory we derive the so called nominal wage equation which establishes a relationship between nominal wages and a distance weighted sum of the volume of economic activities in surrounding locations which is usually known as market potential. The estimation of this equation using Colombian departamental data over the period 1990-2015 reveals that market potential plays a crucial role in explanation of the spatial distribution of per capita income. Moreover the results also show that access to markets became more important over the course of the period under analysis which is pointing to a process of spatial concentration of economic activities in Colombia where the agglomeration forces are more important than the dispersion ones. Finally, two important channels that might be affecting the shaping of the spatial distribution of income were devised, physical and human capital.

Measuring Network Systemic Risk Contributions: A Leave-one-out Approach

Mercredi | 2018-05-24
Salle B103 – 12h00

Sullivan HUE – Sessi TOKPAVI – Yannick LUCOTTE

Granger-causality measures of interconnectedness between financial institutions are useful indicators of systemic risk (Billio et al., 2012, Journal of Financial Economics), as they help to evaluate to which extent the distress of one institution disseminates across the whole financial system due to the network. This article provides a critical assessment of Granger-causality networks, showing that they can lead to inconsistent measures of systemic risk contributions due to the presence of spurious causalities arising from indirect contagion effects. Traditional solutions to control for these effects – via inference on conditional Granger-causality – lead however to the curse of dimensionality. To solve this issue, we provide a measure of financial network systemic risk contributions based on the leave-one-out (LOO) concept. For a given financial institution, the new measure evaluates to which extent the total number of significant Granger-causality breakdowns when this institution is excluded from the system. We control for spurious causalities between the remaining institutions due to the indirect contagion effect of the excluded financial institution using a conditional Granger-causality test, which is free of the curse of dimensionality. Empirical applications are conducted using daily market returns for a sample of the world?s largest banks. Results show that our measure gives a meaningful ranking of the systemic importance of financial institutions which is consistent with the ranking of global systemically important banks (G-SIBs) provided by the Financial Stability Board (FSB). Moreover, our measure appears as a robust significant early-warning indicator of large losses in the case of a systemic event, and is strongly driven by balance-sheet variables related to size, leverage, profitability and bank?s specialization.

Trickle-Down Affirmative Action: A Case Study in Chess

Mardi | 2018-05-22
Salle B103 16h – 17h20


Vertical gender segregation is one of the most stubborn features of labor markets: high-ranking positions are primarily held by men in Business, Politics and Science. Can we implement pro-active steps to erase this segregation? We try to answer this question by investigating the effects of a clear affirmative action for women, where we have a good measure of “ability” even of people who did not directly benefit from the action. Chess, which is grappling with a huge vertical segregation problem, offers a special and unique opportunity to investigate the effect of an affirmative action, because we have a clear idea how good someone is. France introduced an affirmative action (AA) for women in its club competitions in the beginning of the nineties, which helps us to answer two central questions. How much does the AA benefit the selected pool? Does the AA trickle-down? In other words, does it lead to higher investment (benefits) of a whole group and not just those selected?

De l’hyperinflation au  » miracle monétaire » : L’expérience hongroise de 1945-46

Mardi | 2018-05-15
Salle B103 16h – 17h20


Entre août 1945 et juillet 1946, la Hongrie a connu la pire crise inflationniste jamais recensée. Dans les derniers jours de cet épisode, les prix augmentèrent de 150.000% par jour. Dès les travaux de Kaldor ou Nogaro sur cette expérience, plusieurs facteurs ont été mis en avant expliquer le phénomène : dérive des finances publiques, anticipations des acteurs ou introduction d’une monnaie indexée. L’objectif de cet article consiste à revenir sur ces explications et à ajouter une dimension cruciale, celle de l’influence des puissances extérieures. De fait, la prise en compte des stratégies déployées depuis Washington et Moscou permet d’élucider plus complètement la virulence de la crise hongroise. Ainsi, la réussite de la stabilisation, qualifiée de « miracle monétaire » en 1946, est à relativiser.

Voter Turnout and Intergenerational Redistribution

Mardi | 2018-04-24
Salle des thèses 16h – 17h20

Mickael MELKI

Electoral reforms affecting the incentives to vote modify the composition of the electorate, potentially overrepresenting specific interests in policy implementation. Due to the age turnout gap, they may bias intergenerational redistribution in favor of the elderly. We exploit a natural experiment provided by the repeal of mandatory voting in Austria to study how a change in the incentive to vote affects intergenerational redistribution through pro-young public education spending. We find that the reform does not inevitably bias redistribution in favor of the elderly but rather leads to a strong polarization in education policies across municipalities according to their demography.

What is the Investment Loss due to Uncertainty?

Mardi | 2018-04-19
Salle B103 12h – 13h30


We investigate the effect of economic uncertainty on investment. We employ a sample consisting of annual data from 25000 Greek firms’ balance sheets covering the period from 2000 to 2014. A dynamic factor model is employed to proxy uncertainty. The investment performance of 14 sectors is examined within a dynamic investment model. Robust GMM estimates of the investment rate model reveal a high degree of heterogeneity among these sectors. Overall uncertainty affects negatively investment performance and this effect substantially increased in the years of crisis. Agriculture and Mining are the least affected and the most affected ones include Manufacturing, Real Estate and Hotels. Focusing on the response of investment to uncertainty, it emerges that (relative) smaller firms are affected more compared to larger ones.