▼ 

Generalized Auto-regressive Conditional Heteroskedastic (GARCH) models with fixed parameters are typically used to model and predict the volatility of financial time series. When estimating such models a common finding is that conditional variances are strongly persistent, especially for long time series. It has been argued that this feature is due to changes in the parameters of the GARCH process, which are overlooked if the model specification imposes fixed parameters. An interesting way of making GARCH models more flexible is enriching them with a dynamic discrete latent state Markov process in such a way that the parameters can switch from one value to another. These models are called Markov-switching (MS) and Change-point (CP) GARCH models. However estimation of MS- or CP-GARCH models is numerically unfeasible either by the method of maximum likelihood or by the Bayesian approach, given the path dependence problem. The thesis develops three different estimation methods that solve the issue. It also details how to choose the optimal number of regimes. The dissertation then explores numerous aspects of abrupt switching models in the context of financial time series. For instance, evidence of structural breaks in volatility processes is empirically observed in each Chapter.

(ECON 3)  – UCL, 2013

Advisors/Committee Members: UCL - SSH/IMMAQ/CORE - Center for operations research and econometrics, Bauwens, Luc, Van Bellegem, Sébastien, Rombouts, Jeroen, van Dijk, Herman K., Yukai, Yang.

▼ 

Data envelopment analysis (DEA) is a widely used non-parametric method for estimating the relative input-output efficiency for a set of homogenous decision making units (DMUs). Due to its solid underlying mathematical basis and wide applications to real-world problems, much effort has been devoted to DEA models. Though DEA as a well-known methodology provides many advantages relative to other approaches, there are some limitations, complexities and challenges that need to be addressed. It is therefore important to extend the DEA models to fit the real characteristics involving (i) the data generating process (DGP), (ii) the production process, and (iii) the evaluation need. Conventional DEA methods require accurate measurement of both input and output data. However, the observed values of the inputs and outputs in real-world problems are sometimes ambiguous, uncertain and imprecise. In the first aspect of this thesis, we deal with such imperfect data in measuring the managerial and operational efficiency of firms along with providing a robust ranking order when both input and output data are imprecise. In the second aspect, we show how to apply DEA methods in multilevel structures such as supply chains, also in the presence of uncertainty. In the third aspect, we develop a fuzzy DEA model with imprecise and ambiguous data in order to evolve the scope of application to a larger set of real-life problems. Finally, we propose a two-stage algorithm to extend the DEA model using a common set of input and output weights (CSW).

(IAG 3)  – UCL, 2013

Advisors/Committee Members: UCL - SSH/IMMAQ/CORE - Center for operations research and econometrics, Agrell, Per Joakim, Chevalier, Philippe, Emrouznejad, Ali, Vandeneeckaut, Philippe, Simar, Léopold, Korhonen, Pekka.

▼ 

In this thesis we consider different joint production and transportation problems. We first study the simplest two-level problem, the uncapacitated two-level production-in-series lot-sizing problem (2L-S/LS-U). We give a new polynomial dynamic programming algorithm and a new compact extended formulation for the problem and for an extension with sales. Some computational tests are performed comparing several reformulations on a NP-Hard problem containing the 2L-S/LS-U as a relaxation. We also investigate the one-warehouse multi-retailer problem (OWMR), another NP-Hard extension of the 2L-S/LS-U. We study possible ways to tackle the problem effectively using mixed integer programming (MIP) techniques. We analyze the projection of a multi-commodity reformulation onto the space of the original variables for two special cases and characterize valid inequalities for the 2L-S/LS-U. Limited computational experiments are performed to compare several approaches. We then analyze a more general two-level production and transportation problem with multiple production sites. Relaxations for the problem for which reformulations are known are identified in order to improve the linear relaxation bounds. We show that some uncapacitated instances of the basic problem of reasonable size can often be solved to optimality. We also show that a hybrid MIP heuristic based on two different MIP formulations permits us to find solutions guaranteed to be within 10% of optimality for harder instances with limited transportation capacity and/or with additional sales. For instances with big bucket production or aggregate storage capacity constraints the gaps can be larger. In addition, we study a different type of production and transportation problem in which cllients place orders with different sizes and delivery dates and the transportation is performed by a third company. We develop a MIP formulation and an algorithm with a local search procedure that allows us to solve large instances effectively.

(FSA 3)  – UCL, 2011

Advisors/Committee Members: UCL - SSH/IMMAQ/CORE - Center for operations research and econometrics, Wolsey, Laurence, Agrell, Per, Glineur, François, Van Vyve, Mathieu, Chevalier, Philippe, Wagelmans, Albert.

▼ 

Renewable energy integration has progressively challenged the operating assumptions of electricity markets, questioning at first the deterministic nature of day-ahead and other forward electricity markets. As the integration of renewable resources became deeper, transmission grids began to experience congestion in unforeseen, dynamic and uncertain patterns, questioning now the management of transmission constraints in electricity markets. This dissertation proposes detailed models and algorithms for analyzing the impacts of uncertain renewable supply on different transmission-constrained electricity market designs, using parallel computing extensively in order to solve large-scale mathematical programs and to carry out simulations under different operating conditions for realistic systems. The contributions of the dissertation are organized in three chapters. Chapter 2 presents an asynchronous distributed algorithm for solving the stochastic unit commitment problem. The algorithm, deployed in parallel, is able to solve realistic instances of stochastic unit commitment within operationally acceptable tolerances and solution times. Chapter 3 proposes a consistent framework for modelling different zonal electricity markets. We develop cutting-plane algorithms to incorporate the N-1 criterion into this framework and we conduct simulations using single-period models for the Central Western European system under 768 000 different operating conditions. In chapter 4, we propose a hierarchy of mathematical programs that model the European zonal electricity market organization in detail in a multi-period setting. We compare the performance of this organization to the performances of a nodal market and the stochastic unit commitment model on the Central Western European system. Numerical results in chapters 3 and 4 indicate that failing to account for the limitations of the transmission grid, in a regime of large-scale renewable energy integration, can undermine system performance to much a larger extent than failing to account for uncertainty in nodal electricity markets.

(FSA - Sciences de l'ingénieur)  – UCL, 2018

Advisors/Committee Members: UCL - SSH/IMMAQ/CORE - Center for operations research and econometrics, UCL - Ecole Polytechnique de Louvain, Papavasiliou, Anthony, Chevalier, Philippe, Smeers, Yves, Van Vyve, Mathieu, Lulli, Guglielmo.

▼ 

In the global effort to achieve sustainable development, new adaptive approaches of urban planning call for a reliable understanding of Urban Morphodynamics: the evolution of the spatial structure of an urban system from elementary interactions between its components. In this thesis, theoretical and methodological contributions to Urban Morphodynamics are proposed from the integration of the two main strands of literature in quantitative urban geography: Location Theory, which studies the economic determinants of the location of economic activities, and Complex Systems, which describe how cities self-organize from the dynamic interactions of many individuals. After an historical review in the first part, its second part addresses two problems of Urban Morphodynamics, gathering concepts and methods from both Location Theory and Complex Systems. First, using mathematical modelling, it exposes the scaling properties of the equilibrium monocentric city model. Second, coupling analytical developments with agent-based simulations, it explores the dynamic growth of a non-monocentric city model. In a third part, it proposes a hybrid modelling framework that combines the behavioural foundations of Discrete Choice Theory with the nonlinear dynamic models of Synergetics. This framework is then applied to a core-periphery model of New Economic Geography in order to forecast regional development trajectories. In a fourth and last part, in light of the proposed models, this thesis argues that the theoretical foundations of Location Theory and Complex Systems can be reconciled in an operational urban morphodynamic theory.

(SC - Sciences)  – UCL, 2018

Advisors/Committee Members: UCL - SSH/IMMAQ/CORE - Center for operations research and econometrics, UCL - Faculté des Sciences, Peeters, Dominique, Thomas, Isabelle, De Keersmaecker, Marie-Laurence, Tharakan, Joe, Caruso, Geoffrey, Nicolini, Rosella, Arcaute, Elsa.

▼ 

The dissertation can be divided into two parts. The first part is composed of one chapter focusing on information aggregation in a game theory model; the second part is composed of two chapters focusing on the link between pension schemes and economic growth. In Chapter 1, we define renegotiation-proof equilibria when players indirectly communicate through a public signal aggregating their private information. The result is of particular economic interest, as in most of economic activities prices aggregate and partially reveal the private information of each economic agent. In Chapter 2, we study the relation between pension schemes and financial intermediation in an overlapping generations model with Schumpeterian growth and consumption shocks. We show that a financial intermediary may be unable to adequately isolate consumers from the shocks, making a funded pension scheme equivalent to a research and production subsidy for the economy. In Chapter 3, we propose a new hybrid pension scheme. In recent years, governments have phased out pay-as-you-go pension schemes in favour of funded ones. Instead of dropping the intergenerational transfers of the pay-as-you-go pensions, we propose to invert them. Resources would flow from old generations to young ones, as if it were a system of public bequests. We show that the public bequests scheme outperforms the canonical pension schemes.

(ECGE - Sciences économiques et de gestion)  – UCL, 2018

Advisors/Committee Members: UCL - SSH/IMMAQ/CORE - Center for operations research and econometrics, UCL - Faculté des sciences économiques, sociales, politiques et de communication, Davila, Julio, Nava, Francesco, Pensieroso, Luca, Vannetelbosh, Vincent, Maniquet, François.

▼ 

Many real-world problems can be formulated in the framework of mixedinteger programming. This includes many problems in routing, scheduling and other fields, which affect our everyday lives, but are seemingly invisible. Solving such problems of practical size can be difficult even on very powerful computers. This makes it necessary to develop new, better formulations and methods of approaching them. This dissertation studies methods of strengthening the formulations of three problems related to networks that fall under this framework. Chapter 1 gives a short introduction into the field of mathematical optimization. Chapter 2 presents contribution to a strong extended formulation for the convex recoloring problem, which has application in analysing the phylogenetic trees. Chapter 3 proposes and studies a new hierarchy of improving path-based extended formulations for the Steiner tree problem, which has applications in computational biology and network routing and wiring. It shows that this hierarchy provides better lower bounds on the so-called integrality gaps than currently used approaches. Chapter 4 considers the optimal power flow problem with additional binary variables related to decision, whether a power plant is scheduled for operation. It uses the recent semidefinite programming relaxation approach to the problem and studies polyhedral structure of subsets of constraints related to single nodes in the network.

(FSA - Sciences de l'ingénieur)  – UCL, 2018

Advisors/Committee Members: UCL - SSH/IMMAQ/CORE - Center for operations research and econometrics, UCL - Ecole Polytechnique de Louvain, Van Vyve, Mathieu, Chevalier, Philippe, Glineur, François, Louveaux, Quentin, Papavasiliou, Anthony, Poss, Michael.

▼ 

This thesis evaluates the performance of bicycle sharing systems (BSS), autonomous systems of accessible bicycles that can be easily used for one way trips, and determines whether they are successful at achieving promoted social and environmental outcomes through quantitative and qualitative methods. Such systems are typically surrounded by positive narratives of success, health, environmental and social benefits. This work challenges these notions. This thesis begins with the formalisation of BSS station level and trip data revealing alternative data contained within. Combined with spatiotemporal data analysis, this allows the estimation of trips, a potential measure of success. Due to most operators not providing consistent or comparable metrics of usage this work opens this heavily promoted technological transport innovation’s performance for public scrutiny. Performance estimates of 75 case studies show a majority having less than two trips per day per bicycle, suggesting a poor investment, regardless of existing social justice issues and exaggerated environmental benefits. Using this metric this work determines which attributes impact performance. While station density and cycling infrastructure, among others, are found to impact performance, results challenge promoted practice. Formalisation yielded rebalancing, the moving of bicycles to adjust to demand exceeding supply. Spatiotemporal data analysis and interviews with operators provides the first description of applied rebalancing, providing an alternative perspective to the many theoretical optimisation models. Results show rebalancing is spatially selective and influencing BSS outcomes, potentially contrary to its purpose. Finally, this thesis, through a critical urban sustainability perspective, presents darker aspects of BSS, beyond the golden narratives, showing conflicts of interest, controversy and the commercialisation of an initially environmental and anti-consumerism concept. Existential questions are raised due to BSS, mostly privately operated, providing benefits to an already advantaged class while public space is privatised and urban advertising increased. This work concludes by suggesting that alternative investment to bicycle sharing systems, such as cycling infrastructure, may be more beneficial and just.

(SC - Sciences)  – UCL, 2016

Advisors/Committee Members: UCL - SSH/IMMAQ/CORE - Center for operations research and econometrics, UCL - Faculté des Sciences, Caruso, Geoffrey, Hesse, Markus, Thill, Jean-Claude, Karvonen, Andrew, Chevalier, Philippe, Thomas, Isabelle.

▼ 

The increasing availability of high-quality transaction data across many financial assets, allow the construction of estimates of ex-post daily realized volatility and co-volatility by summing squares and cross-products of intraday high-frequency returns. This exhaustive set of data has stimulated the development of a lively field of econometric analysis with the proposition of models directly fitted to time series of realized measures. One interest of these models is that they can be used for forecasting future values, which is typically of use in financial applications such as hedging, option pricing, risk management, and portfolio allocation. (Multivariate) GARCH models can be used for the same purposes but since they rely on daily observed returns, in principle they provide less precise estimates and forecasts of variances and covariances than measures based on intraday data. The present thesis tries to contribute to the existing literature by proposing feasible models for realized covariance matrices that can be readily applied in financial applications. The common feature of the novel specifications is a dynamic temporal structure of the covariance matrix consisting of a short-term and a long-term component, whereby the long-term component can be shaped differently depending on the specific problem at hand. Throughout the thesis we firstly embrace the common belief of a constant long-run component and then we relax it, thus illustrating the main strengths and weaknesses of both approaches. Furthermore, in each case, we propose our own methodology to allow estimation for large cross-sections, thus mitigating the common issue of parameter proliferation that prevents the application of many models to realistic high-dimensional frameworks. The usefulness of the proposed procedures is supported by extensive empirical evidence.

(ECGE - Sciences économiques et de gestion)  – UCL, 2016

Advisors/Committee Members: UCL - SSH/IMMAQ/CORE - Center for operations research and econometrics, UCL - Faculté des sciences économiques, sociales, politiques et de communication, Boudt, Chris, Grigoryeva, Lyudmila, Van Bellegem, Sèbastien, Bauwens, Luc, Hafner, Christian, Storti, Giuseppe.

▼ 

Land use and transport interactions (LUTI) models are widely employed by planners, to forecast future urban patterns and to test the influence of land use or transport policies. This thesis examines their sensitivity to two types of spatial bias, the choice of the study area (“spatial extent”) and of the areal units (“spatial resolution”). The first part of this thesis focuses on econometric components inside LUTI models. We propose two extensions to the literature on the Modifiable Areal Unit Problem (MAUP). First, the sensitivity of regression models to spatial extent is examined. Secondly, the influence of the spatial resolution on discrete choice models, used by most state-of-the-art LUTI models to forecast location choices of agents, is assessed. Significant variations are found in parameter estimates, leading to changes in the behaviour of the model. The second part of the thesis assesses the influence of these spatial biases on LUTI models’ outputs. Two applications of the UrbanSim model are developed. We rely on a synthetic case study to examine the sensitivity of the final situation predicted by the model. Then, a model of the urban region of Brussels is used to explore the implications of this sensitivity for policy evaluation. The results show that variations induced by spatial bias on LUTI models’ outputs are larger than those due to transport or land use scenarios, and that they affect the estimation of the sustainability of these scenarios. The last chapter offers recommendations to reduce the sensitivity of LUTI models to these spatial biases, consisting in the adoption of “best spatial practices” and of potential technical development, together with alternative approach of increasing the applicability of LUTI models.

(SC - Sciences)  – UCL, 2016

Advisors/Committee Members: UCL - SSH/IMMAQ/CORE - Center for operations research and econometrics, UCL - Faculté des Sciences, Thomas, Isabelle, Peeters, Dominique, Caruso, Geoffrey, Gerber, Philippe, Jourquin, Bart, Dekeermaecker, Marie-Laurence.

▼ 

This dissertation in microeconomic theory is composed of four chapters. The first two chapters investigate two closely related normative questions. How can we compare different distributions of a multi-goods endowment among individuals that care for their relative situation? How can we compare the poverty in different income distributions when both the absolute and relative aspects of income matter? The outputs of these chapters are indicators able to rank economic outcomes as a function of their adequacy with the principles of Pareto efficiency and equality of resources. The third chapter aims at comparing different mechanisms used for the allocation of economic resources among individuals holding private information, e.g. their preferences over these resources. This implies studying both the incentives these mechanisms provide and the properties of the allocations to which they lead. The chapter proposes a general criterion for comparing the performance of allocation mechanisms and apply this criterion to the stability of school choice mechanisms. The last chapter focuses on the strategic interactions between individuals averse to ambiguity. It proposes a new interpretation for equilibria in ambiguous randomization strategies.

(POLS - Sciences politiques et sociales)  – UCL, 2015

Advisors/Committee Members: UCL - SSH/IMMAQ/CORE - Center for operations research and econometrics, UCL - Faculté des sciences économiques, sociales, politiques et de communication, d'Aspremont, Claude, Steg, Jan-Henrik, Kirchsteiger, Georg, Riedel, Frank, Weymark, John, Maniquet, François.

▼ 

In this PhD dissertation, we investigate how to solve some classical combinatorial optimization problems in network flows and their applications, using secure multiparty computation. Our study highlights the differences between traditional and secure adaptations of some algorithms to later test its implementation. It also explores various trade-offs between performance and security. We provide protocols that can be used as building blocks to solve more complex problems. Additionally, we report on practical applications, more specifically, we study the problem of securely building auction mechanisms with transmission constraints. We focus on improving performance for real life applications. We report on the design of a specific Object Oriented implementation of the necessary secure multiparty computation protocols used for the experimentation on practical applications. Areas of interest for our work can be found in: auction markets, communication networks, routing data from rival company hubs, distribution problems, amongst others.

(FSA - Sciences de l'ingénieur)  – UCL, 2015

Advisors/Committee Members: UCL - SSH/IMMAQ/CORE - Center for operations research and econometrics, UCL - Ecole Polytechnique de Louvain, Van Vyve, Mathieu, Chevalier, Philippe, Pereira, Olivier, Wolsey, Laurence, Spieksma, Frits, Standaert, François-Xavier.

▼ 

Nowadays, the improvements in obtaining and processing information and the development of big data are increasingly important matters from an ethical as well as an economic viewpoint. On the one hand, such phenomena imply the access to individuals’ sensitive information raising issues concerning their privacy. On the other hand, firms show clear-cut incentives to engage in targeting strategies such as personalised rebates, bring-a-friend rewards, targeted prices in online social networks. The goal of this thesis is to provide some theoretical explanation of the incentives of firms to use the information and how the distribution of surplus is affected by that use. The manuscript is divided into three chapters, each one readable as a distinct paper. The first two chapters investigate the consequences of pricing policies based on the past purchase behaviour of consumers in markets characterised by horizontal and vertical differentiation (Chapter 1) and by cross-group network externalities (Chapter 2), whereas the third one proposes a network-based analysis of referral bonuses (Chapter 3). The first paper demonstrates that firms might converge to asymmetric pricing behaviours leading to one-direction switching. These equilibrium behaviours lead to the exit of the low-quality firm the market and, under certain conditions, will result in a detriment for consumers in relation to uniform pricing, overturning the welfare results of the previous literature. The second paper presents a model of two-sided markets in which, after a first round of purchases, platforms are allowed to price-discriminate in the subscribers’ side. The model shows that stronger cross-group externalities make two-direction switching less probable. Moreover, second-period competition is strengthened compared to the case intra-side uniform pricing, whereas in the first period it is relaxed if subscribers exhibit stronger externalities than firms. The model presented in Chapter 3 shows how the level of referral bonuses strongly depends on the distribution of connections in the social network. While in random networks, the bonus is set in such a way that roughly the most popular half of informed consumers spread the voice, in scale-free networks we expect a bonus such that only the very connected people are incentivased.

(ECGE - Sciences économiques et de gestion)  – UCL, 2015

Advisors/Committee Members: UCL - SSH/IMMAQ/CORE - Center for operations research and econometrics, UCL - Faculté des sciences économiques, sociales, politiques et de communication, Bourreau, Marc, Pin, Paolo, Esteves, Rosa-Branca, Belleflamme, Paul, Toulemonde, Eric, Baland, Jean-Marie.

▼ 

This thesis introduces, as major contribution, a new definition of strategically stable set of equilibria by considering a new class of perturbed games obtained by adding a set of irrelevant players and a collection of dominated strategies to the initial game. Both variations have no effect on the set of equilibria of the original game but allow to widen the resulting stable sets of equilibria up to satisfy all the properties proposed in Kohlberg and Mertens [1986] and in Mertens [1989]. Besides a new fictitious game is proposed to define a new single valued Nash equilibrium refinement, namely refined equilibria, and to extend strategic stability to correlated equilibria. In both cases the desired goals are not reached even if there are significant positive results: a refined equilibrium satisfies the invariance property improving on the concept of proper equilibrium. This result stems from a setting that is closer to the forward induction than the backwards induction approach: a single valued solution concept that always conforms with backwards induction cannot verify the property of invariance. Similarly the concept of stable correlated equilibria improve on both perfect and acceptable correlated equilibria since it can be applied to nplayer games and it excludes equilibria that are not perfect.

(POLS - Sciences politiques et sociales)  – UCL, 2015

Advisors/Committee Members: UCL - SSH/IMMAQ/CORE - Center for operations research and econometrics, UCL - Faculté des sciences économiques, sociales, politiques et de communication, Vannetelbosch, Vincent, Van Bellegem, Sébastien, Minelli, Enrico, D’Aspremont, Claude, Dehez, Pierre.

▼ 

The thesis addresses three issues related to endogenous discounting, habits in consumption and consumption externalities. In the first chapter, we build a model where the discount rate is endogenous and the production function is able to deliver endogenous growth. We show that with a utility function restricted to take positive values, the model generates an optimal path in accordance with empirical evidence concerning the positive correlation between increasing savings and growth rates, the twin-peaks of economic growth as well as the existence of growth miracles and disasters. In the second chapter, we study a model where agents possess habits in consumption and care about environmental quality. We show that the competitive equilibrium can be characterized by endogenous fluctuations implying the breakdown of different sustainability criteria. Short-run fluctuations can also be present in the optimal case suggesting that we can solve for environmental externalities but not for the sustainability problem if we stick to a standard welfare function without any sustainability constraint. Finally, in the third chapter, we build a model with an endogenous discount rate and consumption externalities affecting both the discount rate and the production function. This allows the existence of multiple equilibria, indeterminacy, cyclical-motions as well as take-offs and depressions through local bifurcations. Unbounded growth is also a possibility in this framework and generates always a unique indeterminate balanced growth path. An appropriate policy should implement a consumption subsidy or tax depending on the magnitude of both kinds of externalities.

(ECGE - Sciences économiques et de gestion)  – UCL, 2014

Advisors/Committee Members: UCL - SSH/IMMAQ/CORE - Center for operations research and econometrics, UCL - Faculté des sciences économiques, sociales, politiques et de communication, Davila, Julio, Boucekkine, Raouf, de la Croix, David, Venditti, Alain, Mariani, Fabio.

▼ 

This thesis consists of three essays studding the influence of heterogeneity upon the economic dynamics. In the first model of R&D-based economic growth the agents have heterogeneous preferences over a growing continuum of consumption goods. In the second model a monopolist firm or an industry distributes investments in physical capital among a growing set of technologies the payoff of which is heterogeneous. In the third model of solving territorial disputes between countries the income from the land use of a country is not equally (heterogeneously) distributed among the citizens.

(ECGE - Sciences économiques et de gestion)  – UCL, 2014

Advisors/Committee Members: UCL - SSH/IMMAQ/CORE - Center for operations research and econometrics, UCL - Faculté des sciences économiques, sociales, politiques et de communication, Julio, Davila, Carmen, Camacho, Vladimir, Veliov, Raouf, Boucekkine, Mathieu, Parenti.

▼ 

This Ph.D. dissertation develops theories of dynamic social influence. In a dynamic framework, individuals interact repeatedly with their social environment and exchange beliefs and opinions on various economic, political and social issues. In Chapter 2, we study influence processes modeled by ordered weighted averaging operators. These operators are anonymous: they only depend on how many agents share a belief. We find a necessary and sufficient condition for convergence to consensus and characterize outcomes where the society ends up polarized. Furthermore, we apply our results to fuzzy linguistic quantifiers. In Chapter 3, we introduce the possibility of manipulation into the model by DeGroot (1974). We show that manipulation can modify the trust structure and lead to a connected society. Manipulation fosters opinion leadership, but the manipulated agent may even gain influence on the long-run beliefs. Finally, we investigate the tension between information aggregation and spread of misinformation. In Chapter 4, we introduce conflicting interests into a model of non-Bayesian belief dynamics. Agents meet with their neighbors in the social network and exchange information strategically. With conflicting interests, the belief dynamics typically fails to converge: each agent's belief converges to some interval and keeps fluctuating on it forever.

Cette dissertation de doctorat développe des théories de l'influence sociale dynamique. Dans un cadre dynamique, les individus interagissent à plusieurs reprises avec leur environnement social et échangent leurs croyances et opinions sur différentes questions économiques, politiques et sociales. Dans le Chapitre 2, nous étudions les processus d'influence modélisés par les moyennes ordonnées pondérées. Ces dernières sont anonymes : elles ne dépendent que du nombre d'agents qui partagent la même croyance. Nous exhibons une condition nécessaire et suffisante pour la convergence au consensus et caractérisons les résultats où la société se retrouve polarisée. Enfin, nous appliquons nos résultats aux quantificateurs linguistiques flous. Dans le Chapitre 3, nous introduisons la possibilité de manipulation dans le modèle de DeGroot (1974). Nous montrons que la manipulation peut modifier la structure de confiance et mène à une société connectée. La manipulation promeut le leadership d'opinion, mais même l'agent manipulé peut gagner de l'influence sur les croyances à long terme. Finalement, nous étudions la tension entre l'agrégation d'informations et le déploiement de désinformations. Dans le Chapitre 4, nous introduisons des conflits d'intérêt dans un modèle de dynamique de croyance non-bayésienne. Les agents se rencontrent avec leurs voisins dans le réseau social et échangent des informations stratégiquement. Avec des conflits d'intérêt, la dynamique de croyance ne converge pas en général : la croyance de chaque agent converge vers un certain intervalle et continue à fluctuer sur celui-ci pour toujours.

(ECGE - Sciences économiques et de gestion)  – UCL, 2014

Advisors/Committee Members: UCL - SSH/IMMAQ/CORE - Center for operations research and econometrics, UCL - Faculté des sciences économiques, sociales, politiques et de communication, Rusinowska, Agnieszka, Vannetelbosch, Vincent, Grabisch, Michel, López-Pintado, Dunia, Herings, Jean-Jacques, Mauleon, Ana, Bloch, Francis.

▼ 

The thesis addresses three questions related to the main goals of elections, preference aggregation and politicians’ accountability. In the first chapter, we explore the effect of adopting a closed or open list proportional representation system on the representation of minorities in Parliaments. The two systems differ in the possibility for the electorate to express preferential votes for candidates within party-lists. We show that minorities are proportionally represented only under open list, if voters can vote for a limited number of candidates. In all other cases, minorities are poorly represented, or not represented at all. The second chapter provides an explanation for sub-optimal policy making decisions by incumbents. We show that the possibility to stand for re-election can induce them to address less relevant issues, when more relevant ones are too difficult to solve. As failing to solve an issue constitutes a bad signal about their quality, politicians prefer to address easier ones, even if they are less important for the electorate. The goal of the third chapter is to axiomatically characterize a measure of ethnic voting, defined as the extent to which voting decisions are affected by ethnic motivations. The main property we impose on the measure is neutrality with respect to size of ethnic groups and total support of parties. We identify the class of size neutral measures of ethnic voting and investigate monotonicity axioms that are compatible with this property.

(POLS - Sciences politiques et sociales)  – UCL, 2014

Advisors/Committee Members: UCL - SSH/IMMAQ/CORE - Center for operations research and econometrics, UCL - Faculté des sciences économiques, sociales, politiques et de communication, Maniquet, François, Morelli, Massimo, Aldashev, Gani, Castanheira, Micael, Davila, Julio.

▼ 

This thesis contributes four essays to the economic literature on the multivariate modeling of the variance-covariance dynamics in the financial time series data, covering the issues of dynamic hedging, international volatility spillovers and financial integration, where applying the Multivariate GARCH models leads to the efficient resolution of a number of ongoing empirical issues. The first essay addresses the portfolio hedging problem for a range of commodities and proposes an alternative way of accounting the asymmetric effect in the volatility by including the asymmetric term in a multivariate GARCH model. By in- and out-of-sample forecast we show that hedging using the asymmetric model outperforms other alternatives. The second essay aims to investigate the cross-border effect of the monetary policy rate announcements on the comovements of the world's major stock markets. The news component of the announcements is extracted from the interest rate futures data. Both the effect of the magnitude and sign of the news are considered. It is demonstrated how these effects may alter the asset allocation decisions. The third essay contributes to the better understanding of the financial integration and volatility, i.e. the risk, transmission across European stock markets and provides comprehensive evidence by using a fully flexible multivariate model. The results are of high practical importance, since the high degree of integration implies higher vulnerability of a country to external risks. On the other, they have considerable implications for financial market participants who are involved in hedging and/or portfolio diversification.

(POLS - Sciences politiques et sociales)  – UCL, 2013

Advisors/Committee Members: UCL - SSH/IMMAQ/CORE - Center for operations research and econometrics, UCL - Faculté des sciences économiques, sociales, politiques et de communication, Hafner, Christian, Laurent, Sébastien, Wouters, Raf, Van Bellegem, Sébastien, Bauwens, Luc.

▼ 

Most developed countries nowadays face environmental, health and mobility problems as a consequence of widespread car use. Policies are now being reappraised in favour of more sustainable modes of transport. In particular, bicycle use holds the potential to provide a ‘green’ and healthy alternative to car commuting. There are however still important barriers that discourage people cycling… This thesis aims at identifying some of the main factors that influence cycle commuting and cycling accidents. Identifying such factors would in turn provide greater support to enable policy makers developing supportive environmental conditions for cycling. In the first part of this thesis, we examine which factors influence the spatial variation of bicycle use for commuting to work at the level of the municipalities in Belgium. Special attention is paid to bicycle-specific factors and spatial econometric methods are used to account for the presence of spatial effects in the data. The second part of this thesis examines which factors are associated with cycling accidents in Brussels. Spatial point pattern methods extended to networks are used to compare the ‘locational tendencies’ of cycling accidents officially registered by the police with those that are unregistered. An innovative case-control approach, based on a rigorous sampling design of controls and an exhaustive data collection of spatial factors, is also proposed to allow modelling the risk of cycling accident along the Brussels’ road network. This thesis not only provides sound recommendations helping planners and policy makers to encourage bicycle use, but it also offers new research directions for pinpointing locations where accidents are more likely to occur.

(GEOG 3)  – UCL, 2011

Advisors/Committee Members: UCL - SSH/IMMAQ/CORE - Center for operations research and econometrics, Thomas, Isabelle, De Keersmaecker, Marie-Laurence, Peeters, Dominique, Dujardin, Claire, Int Panis, Luc, Verhetsel, Ann, Vickerman, Roger W..

▼ 

This thesis contributes four essays to the theoretical literature of Economic Growth and Development covering issues of environment, optimal taxation, demography, gender inequality, endogenous technological progress, and comparative development in variations of overlapping generations modelling. The first essay addresses tax and transfer policies to conduct a Diamond (1965) overlapping generations economy with environmental externalities to the social optimum through Pareto-improving path. The second essay studies the role of geographical and environmental conditions as well as a mechanism under which an society can be locked in a stagnation characterized by a small population, zero-education, and low level of technology. The third essay studies the comparative development across societies by considering the differences in geographical advantage for agricultural production between societies. This essay shows that the geographical advantage for agriculture helps a society to be more prosperous in the agricultural regime, but delays its timings of industrialization and demographic transition. The last essay develops a unified growth model and proposes a new mechanism linking technology, gender inequality, and fertility to explain some stylized facts during the development process. It sheds a light that the evolution from Malthusian stagnation, through the demographic transition, to modern sustained growth along with the improvement in gender equality in education (income), and an increasing female labor supply are inevitable outcomes of the development process.

(ECGE - Sciences économiques et de gestion)  – UCL, 2013

Advisors/Committee Members: UCL - SSH/IMMAQ/CORE - Center for operations research and econometrics, UCL - Faculté des sciences économiques, sociales, politiques et de communication, Davila, Julio, de la Croix, David, Hindriks, Jean, Le Van, Cuong, Parenti, Mathieu.

▼ 

In recent years, we have seen an explosion of data collected from individuals, firms, or countries across short or long periods of time. This type of data gives us an opportunity to study the dynamics of change while controlling for time-invariant unobserved heterogeneity. Unfortunately, this type of heterogeneity, which is usually in the form of individual-specific fixed effects, creates problems for identification, estimation, and inference, especially if we continue to use default procedures without modification or without critical exploration. This dissertation revolves around a common theme – what practices and methods can be considered appropriate responses to the incidental parameter problem in panel data models. My approach to research is firmly rooted in the examination of empirical and theoretical practices so that we can come to an understanding of what we can and cannot do.

(ECGE - Sciences économiques et de gestion)  – UCL, 2016

Advisors/Committee Members: UCL - SSH/IMMAQ/CORE - Center for operations research and econometrics, UCL - Faculté des sciences économiques, sociales, politiques et de communication, Boswijk, Peter, Van Bellegem, Sébastien, Hafner, Christian, Bun, Maurice, Dhaene, Geert, van Garderen, Kees Jan, van Giersbergen, Noud, Kleibergen, Frank.

▼ The rapid growth of firms worldwide causes that relationships in supply chains become more complex, the competition between firms become stronger and customer ask for more demanding products and services. All these changes trigger that a firm looks for opportunities to get more from their scarce resources or to use resources that are beyond its direct control. Thus, a firm can achieve competitive advantages by setting partnerships with other supply chains in order to increase its production capacity, by adapting its operations and pricing strategies to the requirements of the market, and by differentiating between customers according to necessities and willingness to pay for its offered products. We start by studying how firms with similar supply chain roles can collaborate in their operations. Through this collaboration, the firms can mutually benefit from the synergies of pooling operations. A successful collaboration should be efficient in reducing the global cost of the firms. Nevertheless, the willingness of each firm to collaborate may also depend on the fairness of the global cost allocation. In order to guide joint operations, we propose a novel approach that gives priority to the firm that tends to benefit less from the collaboration. In particular, our approach balances the global cost reduction and the inequalities of allocating such cost. Moreover, when analyzing the effect of the uncertainty on the collaboration, our approach shows a high efficiency in reducing risk in comparison to other approaches. We continue by studying how a firm can coordinate its pricing strategy and production and inventory decisions in order to compete with other firms in terms of the prices offered to the customers. We propose a framework for simultaneously planning prices and operations of a firm. We model the operations of the firms as a Lot sizing problem, so computing equilibrium between the prices becomes a time demanding task. We reduce significantly the computational time by providing bounds for the profits that firms can achieve by selecting a pricing strategy. Also, we show the convenience for the firms of using dynamic pricing strategy instead of static pricing strategy, and we show the negative effects that may arise when increasing production capacities. We also study how a firm can gain from differentiating the demand of their customers based on profits and manufacturing requirements. Our study is motivated by the case of a firm that faces two types of demand: on the one hand there are the socalled regular orders that have a relatively long lead time; on the other hand there are urgent orders, whose delay is much shorter but their margins are higher. We study the order acceptance problem for a firm that serves two classes of demand over an infinite horizon. The firm has to decide whether to accept a regular order (or equivalently how much capacity to set aside for urgent orders) in order to maximize its profit. We formulate this problem as a multi-dimensional Markovian Decision Process. We propose a family of… Advisors/Committee Members: UCL - SSH/ILSM - Louvain School of Management Research Institute, UCL - SSH/IMMAQ/CORE - Center for operations research and econometrics, UCL - Louvain School of Management, Chevalier, Philippe, Agrell, Per, Papier, Felix, Roels, Guillaume, Tancrez, Jean-Sébastien, Vandaele, Nico, Wolsey, Laurence.