A análise fatorial é uma importante ferramenta estatística que tem amplas aplicações práticas e explica a correlação entre um grande número de variáveis observáveis em termos de um pequeno número de variáveis não observáveis, conhecidas como variáveis latentes. A proposta deste trabalho é fazer a análise Bayesiana, que incorpora à análise o conhecimento que se tenha sobre os parâmetros antes da coleta dos dados, do modelo fatorial dinâmico na classe de modelos elípticos multivariados, assumindo que a um vetor de q séries temporais pode-se ajustar um modelo fatorial com k < q fatores mais um ruído branco, e que a parte latente segue um modelo vetorial auto-regressivo. A classe de modelos elípticos citada acima é rica em distribuições simétricas com caudas mais pesadas que as da distribuição normal, característica importante na análise de séries financeiras. Essa classe inclui as distribuições t de Student, exponencial potência, normal contaminada, entre outras. A inferência sobre os parâmetros foi feita utilizando métodos de Monte Carlo via Cadeias de Markov, com os algoritmos Metropolis-Hastings e Griddy-Gibbs, através da obtenção das distribuições a posteriori dos parâmetros e dos fatores. A determinação da convergência do processo foi feita por técnicas gráficas e pelos métodos de Geweke (1992), de Heidelberger e Welch (1983) e Half-Width. O método foi ilustrado usando dados reais e simulados. / The factor analysis is an important statistical tool that has wide practical applications and it explains the correlation among a large number of observable variables in terms of a small number of unobservable variables, known as latent variables. The proposal of this work is the Bayesian analysis, which incorporates the information we have concerning the parameters before collecting data into the analysis of a dynamical factor model in the class of multivariate elliptical models, where the factors follow a multivariate autoregressive model, assuming that a vector of q time series can be adjusted with k < q factors and a white noise. The class of elliptical models is rich in symmetrical distributions with heavier tails than the normal distribution, which is an important characteristic in financial series analysis. This class includes t-Student, power exponential, contaminated normal and other distributions. The parameters inference was made through Monte Carlo Markov Chain methods, with Metropolis-Hastings and Griddy-Gibbs algorithms, by obtaining the parameters and factors posteriori distributions. The convergence process was made through graphical technics and by Geweke (1992) and by Heidelberger and Welch (1983) and Half- Width methods. The method was illustrated using simulated and real data.

Neste trabalho estendemos os modelos mistos semiparamétricos propostos por Zhang et al. (1998) para uma classe mais geral de modelos, a qual denominamos modelos mistos aditivos semiparamétricos com erros de contornos elípticos. Com essa nova abordagem, flexibilizamos a curtose da distribuição dos erros possibilitando a escolha de distribuições com caudas mais leves ou mais pesadas do que as caudas da distribuição normal padrão. Funções de verossimilhança penalizadas são aplicadas para a obtenção das estimativas de máxima verossimilhança com os respectivos erros padrão aproximados. Essas estimativas, sob erros de caudas pesadas, são robustas no sentido da distância de Mahalanobis contra observações aberrantes. Curvaturas de influência local são obtidas segundo alguns esquemas de perturbação e gráficos de diagnóstico são propostos. Exemplos ilustrativos são apresentados em que ajustes sob erros normais são comparados, através das metodologias de sensibilidade desenvolvidas no trabalho, com ajustes sob erros de contornos elípticos. / In this work we extend the models proposed by Zhang et al. (1998) to a more general class of models, know as semiparametric additive mixed models with elliptical errors in order to allow distributions with heavier or lighter tails than the normal ones. Penalized likelihood equations are applied to derive the maximum likelihood estimates which appear to be robust against outlying observations in the sense of the Mahalanobis distance. In order to study the sensitivity of the penalized estimates under some usual perturbation schemes in the model or data, the local influence curvatures are derived and some diagnostic graphics are proposed. Motivating examples preliminary analyzed under normal errors are reanalyzed under some appropriate elliptical errors. The local influence approach is used to compare the sensitivity of the model estimates.

Apresentamos algumas aplicações de ferramentas estatísticas que são comumente utilizadas na melhoria da qualidade de processos industriais. Inicialmente, desenvolveu-se procedimentos para testar a competência de laboratórios que participam de programas de ensaios de proficiência. Em situações onde os laboratórios medem várias vezes no mesmo ponto, utilizou-se o modelo de erros de medição, proposto por Jaech [39](1985). Além disso, a inferência sobre os parâmetros de tendência aditiva foi generalizada para a classe de distribuições elípticas. A competência dos laboratórios é avaliada pelo teste da razão de verossimilhança generalizada, do qual, obtemos a distribuição exata para a estatística proposta. Em situações onde os laboratórios medem várias vezes em vários pontos e a variável em análise apresenta variações naturais, utilizou-se o modelo com erro nas variáveis. Diante disso, vamos estender o modelo estrutural definido em Barnett [13] (1969) para o modelo ultra-estrutural com réplicas. Neste caso, vamos avaliar não somente a tendência aditiva, mas também, a tendência multiplicativa, ou seja, avaliar a linearidade das medições. As estimativas dos parâmetros foram obtidas via procedimento do algorítmo EM, com isso, desenvolvemos os teste de Wald, razão de verossimilhança e escore para avaliar a competência dos laboratórios. Nos dois modelos propostos, generalizamos o erro normalizado (En) sugerido pelo Guia 43 [37] para testar a competência dos laboratórios participantes de programas de ensaio de proficiência. Apresentamos também, um procedimento para calcular índices de performance para processos univariados e multivariados. Nestes casos, consideramos que a distribuição dos dados segue uma distribuição Normal assimétrica. Além disso, apresentamos uma análise de simulação onde concluímos que a presença de assimetria nos dados pode causar interpretações erradas sobre o processo, quando a distribuição assumida para os dados é a Normal / We present some applications of statistical tools that are used in the improvement of the quality of industrial processes. Initially, we develop procedures to test the ability of laboratories that participate of programs of proficiency test. In situations where the laboratories measure several times in the same point, we use the model of errors of measurement, considered for Jaech [39](1985). Moreover, the inference on the parameters additive bias was generalized for the class of elliptical distributions. The ability of the laboratories is evaluated by the generalized likelihood ratio test, of which, we get the accurate distribution for the statistics proposal. In situations where the laboratories measure some times in some points and the variable in analysis presents natural variations, uses the model with error in the variable. With this, we go to extend the model structural defined in Barnett [13] (1969) for the ultrastructural model with replicate. In this case, we go to not only evaluate the bias additive, but also, the bias multiplicative, that is, to evaluate the linearity of the measurements. The estimates of the parameters had been gotten by the procedure of the EM algorithm, with this, develop of Wald, likelihood ratio and score test to evaluate the ability of the laboratories. In the two considered models, we generalize the normalized error (En) suggested for Guide 43 [37] to test the ability of the participant laboratories of programs of proficiency test. We also present, a procedure to calculate index of performance for univariate and multivariate processes. In these cases, we consider that the distribution of the data follows a skew Normal distribution. Moreover, we present a simulation analysis where we conclude that the presence of asymmetry in the data can cause interpretations missed on the process, when the distribution assumed for the data is the Normal

This thesis is divided in four chapters. The two first chapters introduce a parametric quantile-based estimation method of univariate heavy-tailed distributions and elliptical distributions, respectively. If one is interested in estimating the tail index without imposing a parametric form for the entire distribution function, but only on the tail behaviour, we propose a multivariate Hill estimator for elliptical distributions in chapter three. In the first three chapters we assume an independent and identically distributed setting, and so as a first step to a dependent setting, using quantiles, we prove in the last chapter the asymptotic normality of marginal sample quantiles for stationary processes under the S-mixing condition.<p><p><p>The first chapter introduces a quantile- and simulation-based estimation method, which we call the Method of Simulated Quantiles, or simply MSQ. Since it is based on quantiles, it is a moment-free approach. And since it is based on simulations, we do not need closed form expressions of any function that represents the probability law of the process. Thus, it is useful in case the probability density functions has no closed form or/and moments do not exist. It is based on a vector of functions of quantiles. The principle consists in matching functions of theoretical quantiles, which depend on the parameters of the assumed probability law, with those of empirical quantiles, which depend on the data. Since the theoretical functions of quantiles may not have a closed form expression, we rely on simulations.<p><p><p>The second chapter deals with the estimation of the parameters of elliptical distributions by means of a multivariate extension of MSQ. In this chapter we propose inference for vast dimensional elliptical distributions. Estimation is based on quantiles, which always exist regardless of the thickness of the tails, and testing is based on the geometry of the elliptical family. The multivariate extension of MSQ faces the difficulty of constructing a function of quantiles that is informative about the covariation parameters. We show that the interquartile range of a projection of pairwise random variables onto the 45 degree line is very informative about the covariation.<p><p><p>The third chapter consists in constructing a multivariate tail index estimator. In the univariate case, the most popular estimator for the tail exponent is the Hill estimator introduced by Bruce Hill in 1975. The aim of this chapter is to propose an estimator of the tail index in a multivariate context; more precisely, in the case of regularly varying elliptical distributions. Since, for univariate random variables, our estimator boils down to the Hill estimator, we name it after Bruce Hill. Our estimator is based on the distance between an elliptical probability contour and the exceedance observations. <p><p><p>Finally, the fourth chapter investigates the asymptotic behaviour of the marginal sample quantiles for p-dimensional stationary processes and we obtain the asymptotic normality of the empirical quantile vector. We assume that the processes are S-mixing, a recently introduced and widely applicable notion of dependence. A remarkable property of S-mixing is the fact that it doesn't require any higher order moment assumptions to be verified. Since we are interested in quantiles and processes that are probably heavy-tailed, this is of particular interest.<p> / Doctorat en Sciences économiques et de gestion / info:eu-repo/semantics/nonPublished

In this work we study two problems motivated by Risk Management: the optimal design of financial products from an investor's point of view and the calculation of bounds and approximations for sums involving non-independent random variables. The element that interconnects these two topics is the notion of conditioning, a fundamental concept in probability and statistics which appears to be a useful device in finance. In the first part of the dissertation, we analyse structured products that are now widespread in the banking and insurance industry. These products typically protect the investor against bearish stock markets while offering upside participation when the markets are bullish. Examples of these products include capital guaranteed funds commercialised by banks, and equity linked contracts sold by insurers. The design of these products is complex in general and it is vital to examine to which extent they are actually interesting from the investor's point of view and whether they cannot be dominated by other strategies. In the academic literature on structured products the focus has been almost exclusively on the pricing and hedging of these instruments and less on their performance from an investor's point of view. In this work we analyse the attractiveness of these products. We assess the theoretical cost of inefficiency when buying a structured product and describe the optimal strategy explicitly if possible. Moreover we examine the cost of the inefficiency in practice. We extend the results of Dybvig (1988a, 1988b) and Cox & Leland (1982, 2000) who in the context of a complete, one-dimensional market investigated the inefficiency of path-dependent pay-offs. In the dissertation we consider this problem in one-dimensional Levy and multidimensional Black-Scholes financial markets and we provide evidence that path-dependent pay-offs should not be preferred by decision makers with a fixed investment horizon, and they should buy path-independent structures instead. In these market settings we also demonstrate the optimal contract that provides the given distribution to the consumer, and in the case of risk- averse investors we are able to propose two ways of improving the design of financial products. Finally we illustrate the theory with a few well-known securities and strategies e.g. dollar cost averaging, buy-and-hold investments and widely used portfolio insurance strategies. The second part of the dissertation considers the problem of finding the distribution of a sum of non- independent random variables. Such dependent sums appear quite often in insurance and finance, for instance in case of the aggregate claim distribution or loss distribution of an investment portfolio. An interesting avenue to cope with this problem consists in using so-called convex bounds, studied by Dhaene et al. (2002a, 2002b), who applied these to sums of log-normal random variables. In their papers they have shown how these convex bounds can be used to derive closed-form approximations for several of the risk measures of such a sum. In the dissertation we prove that unlike the log-normal case the construction of a convex lower bound in explicit form appears to be out of reach for general sums of log-elliptical risks and we show how we can construct stop-loss bounds and we use these to construct mean preserving approximations for general sums of log-elliptical distributions in explicit form. / Doctorat en Sciences / info:eu-repo/semantics/nonPublished

This thesis project studies robust portfolio optimization with Expected Short-fall applied to a reference portfolio consisting of Swedish linear assets with stocks and a bond index. Specifically, the classical robust optimization definition, focusing on uncertainties in parameters, is extended to also include uncertainties in log-return distribution. My contribution to the robust optimization community is to study portfolio optimization with Expected Shortfall with log-returns modeled by either elliptical distributions or by a normal copula with asymmetric marginal distributions. The robust optimization problem is solved with worst-case parameters from box and ellipsoidal un-certainty sets constructed from historical data and may be used when an investor has a more conservative view on the market than history suggests. With elliptically distributed log-returns, the optimization problem is equivalent to Markowitz mean-variance optimization, connected through the risk aversion coefficient. The results show that the optimal holding vector is almost independent of elliptical distribution used to model log-returns, while Expected Shortfall is strongly dependent on elliptical distribution with higher Expected Shortfall as a result of fatter distribution tails. To model the tails of the log-returns asymmetrically, generalized Pareto distributions are used together with a normal copula to capture multivariate dependence. In this case, the optimization problem is not equivalent to Markowitz mean-variance optimization and the advantages of using Expected Shortfall as risk measure are utilized. With the asymmetric log-return model there is a noticeable difference in optimal holding vector compared to the elliptical distributed model. Furthermore the Expected Shortfall in-creases, which follows from better modeled distribution tails. The general conclusions in this thesis project is that portfolio optimization with Expected Shortfall is an important problem being advantageous over Markowitz mean-variance optimization problem when log-returns are modeled with asymmetric distributions. The major drawback of portfolio optimization with Expected Shortfall is that it is a simulation based optimization problem introducing statistical uncertainty, and if the log-returns are drawn from a copula the simulation process involves more steps which potentially can make the program slower than drawing from an elliptical distribution. Thus, portfolio optimization with Expected Shortfall is appropriate to employ when trades are made on daily basis. / Examensarbetet behandlar robust portföljoptimering med Expected Shortfall tillämpad på en referensportfölj bestående av svenska linjära tillgångar med aktier och ett obligationsindex. Specifikt så utvidgas den klassiska definitionen av robust optimering som fokuserar på parameterosäkerhet till att även inkludera osäkerhet i log-avkastningsfördelning. Mitt bidrag till den robusta optimeringslitteraturen är att studera portföljoptimering med Expected Shortfall med log-avkastningar modellerade med antingen elliptiska fördelningar eller med en norma-copul med asymmetriska marginalfördelningar. Det robusta optimeringsproblemet löses med värsta tänkbara scenario parametrar från box och ellipsoid osäkerhetsset konstruerade från historiska data och kan användas när investeraren har en mer konservativ syn på marknaden än vad den historiska datan föreslår. Med elliptiskt fördelade log-avkastningar är optimeringsproblemet ekvivalent med Markowitz väntevärde-varians optimering, kopplade med riskaversionskoefficienten. Resultaten visar att den optimala viktvektorn är nästan oberoende av vilken elliptisk fördelning som används för att modellera log-avkastningar, medan Expected Shortfall är starkt beroende av elliptisk fördelning med högre Expected Shortfall som resultat av fetare fördelningssvansar. För att modellera svansarna till log-avkastningsfördelningen asymmetriskt används generaliserade Paretofördelningar tillsammans med en normal-copula för att fånga det multivariata beroendet. I det här fallet är optimeringsproblemet inte ekvivalent till Markowitz väntevärde-varians optimering och fördelarna med att använda Expected Shortfall som riskmått används. Med asymmetrisk log-avkastningsmodell uppstår märkbara skillnader i optimala viktvektorn jämfört med elliptiska fördelningsmodeller. Därutöver ökar Expected Shortfall, vilket följer av bättre modellerade fördelningssvansar. De generella slutsatserna i examensarbetet är att portföljoptimering med Expected Shortfall är ett viktigt problem som är fördelaktigt över Markowitz väntevärde-varians optimering när log-avkastningar är modellerade med asymmetriska fördelningar. Den största nackdelen med portföljoptimering med Expected Shortfall är att det är ett simuleringsbaserat optimeringsproblem som introducerar statistisk osäkerhet, och om log-avkastningar dras från en copula så involverar simuleringsprocessen flera steg som potentiellt kan göra programmet långsammare än att dra från en elliptisk fördelning. Därför är portföljoptimering med Expected Shortfall lämpligt att använda när handel sker på daglig basis.

In this thesis, we present some new results in distribution theory for both discrete and continuous random variables, together with their motivating applications. We start with some results about the Multivariate Gaussian Distribution and its characterization as a maximizer of the Strichartz Estimates. Then, we present some characterizations of discrete and continuous distributions through ideas coming from optimal transportation. After this, we pass to the Simpson's Paradox and see that it is ubiquitous and it appears in Quantum Mechanics as well. We conclude with a group of results about discrete and continuous distributions invariant under symmetries, in particular invariant under the groups $A_1$, an elliptical version of $O(n)$ and $\mathbb{T}^n$. As mentioned, all the results proved in this thesis are motivated by their applications in different research areas. The applications will be thoroughly discussed. We have tried to keep each chapter self-contained and recalled results from other chapters when needed. The following is a more precise summary of the results discussed in each chapter. In chapter \ref{chapter 2}, we discuss a variational characterization of the Multivariate Normal distribution (MVN) as a maximizer of the Strichartz Estimates. Strichartz Estimates appear as a fundamental tool in the proof of wellposedness results for dispersive PDEs. With respect to the characterization of the MVN distribution as a maximizer of the entropy functional, the characterization as a maximizer of the Strichartz Estimate does not require the constraint of fixed variance. In this chapter, we compute the precise optimal constant for the whole range of Strichartz admissible exponents, discuss the connection of this problem to Restriction Theorems in Fourier analysis and give some statistical properties of the family of Gaussian Distributions which maximize the Strichartz estimates, such as Fisher Information, Index of Dispersion and Stochastic Ordering. We conclude this chapter presenting an optimization algorithm to compute numerically the maximizers. Chapter \ref{chapter 3} is devoted to the characterization of distributions by means of techniques from Optimal Transportation and the Monge-Amp\`{e}re equation. We give emphasis to methods to do statistical inference for distributions that do not possess good regularity, decay or integrability properties. For example, distributions which do not admit a finite expected value, such as the Cauchy distribution. The main tool used here is a modified version of the characteristic function (a particular case of the Fourier Transform). An important motivation to develop these tools come from Big Data analysis and in particular the Consensus Monte Carlo Algorithm. In chapter \ref{chapter 4}, we study the \emph{Simpson's Paradox}. The \emph{Simpson's Paradox} is the phenomenon that appears in some datasets, where subgroups with a common trend (say, all negative trend) show the reverse trend when they are aggregated (say, positive trend). Even if this issue has an elementary mathematical explanation, the statistical implications are deep. Basic examples appear in arithmetic, geometry, linear algebra, statistics, game theory, sociology (e.g. gender bias in the graduate school admission process) and so on and so forth. In our new results, we prove the occurrence of the \emph{Simpson's Paradox} in Quantum Mechanics. In particular, we prove that the \emph{Simpson's Paradox} occurs for solutions of the \emph{Quantum Harmonic Oscillator} both in the stationary case and in the non-stationary case. We prove that the phenomenon is not isolated and that it appears (asymptotically) in the context of the \emph{Nonlinear Schr\"{o}dinger Equation} as well. The likelihood of the \emph{Simpson's Paradox} in Quantum Mechanics and the physical implications are also discussed. Chapter \ref{chapter 5} contains some new results about distributions with symmetries. We first discuss a result on symmetric order statistics. We prove that the symmetry of any of the order statistics is equivalent to the symmetry of the underlying distribution. Then, we characterize elliptical distributions through group invariance and give some properties. Finally, we study geometric probability distributions on the torus with applications to molecular biology. In particular, we introduce a new family of distributions generated through stereographic projection, give several properties of them and compare them with the Von-Mises distribution and its multivariate extensions. / Thesis / Doctor of Philosophy (PhD)