Cette thèse de doctorat part du constat qu'un portefeuille de crédit est soumis à plusieurs risques qui proviennent principalement de la qualité de crédit de l'emprunteur et de son comportement de tirage et de pré-paiement sur ses lignes de crédit. Il s'avère que les risques observés sont dynamiques et dépendent de facteurs divers, autant micro que macro-économiques.Nous avons eu la volonté de comprendre l'articulation de ces risques pour avoir une gestion efficace de ceux-ci dans le présent, mais aussi une vision prospective si les conditions économiques changent, cela pour une gestion pro-active. Pour traiter cette problématique, nous avons articulé nos recherches autour de trois axes qui ont abouti à trois chapitres sous forme d'articles.(i) Analyse des changements des notations de crédit en fonction des facteurs de risque.L'utilisation des modèles de migration multi-factoriels nous a permis de reproduire des faits stylisés cités dans la littérature et d'en identifier d'autres. Nous reconstituons aussi le cycle économique entre 2006 et 2014 qui réussit à capter les crises de 2008 et 2012.(ii) Conception d'un modèle de cash-flow qui tient compte de l'évolution des comportements des emprunteurs sous l'influence de leurs environnements micro et macro-économiques.Nous prouvons l'influence de la notation de crédit, du cycle économique, du taux de recouvrement estimé et du taux d'intérêt court terme sur les taux d'utilisation. Ce modèle permet aussi d'obtenir des mesures de risque comme le Cash Flow-at-Risk et le Stressed Cash Flow-at-Risk sur des portefeuilles de crédit grâce à des simulations de Monte Carlo.(iii) Réflexion sur la Disposition-à-Payer (DAP) d'un décideur neutre à l'ambiguïté pour réduire le risque en présence d'incertitude sur les probabilités. Nous montrons que la présence de plusieurs sources d'ambiguïté (possiblement corrélées) change le bien-être d'un décideur averse au risque bien que celui-ci soit neutre à l'ambigüité / This thesis starts from the observation that a credit portfolio is subject to several risks, mainly due to the credit quality of the borrower and his behavior toward his credit lines (drawdown or prepayment). It turns out that the observed risks are dynamic and depend on various factors, both micro and macroeconomic. Our goal in one hand is to understand the articulation of these risks in order to efficiently manage them in the current time, in the other hand, we want to have a forward looking vision of these risks with respect to the changes in the economic conditions in order to have a pro-active management. To address our objectives, we have articulated our research on three axes that have resulted in three chapters in the form of articles.(i) Analysis of changes in the credit ratings with respect to risk factors. The use of factor migration models allowed us to reproduce some stylized facts mentioned in academic literature and to identify some others. We have also estimated the business cycle between2006 and 2014, which manages to capture the crises of 2008 and 2012.(ii) Design of a cash-_ow model that considers the changes in borrowers' behavior under the influence of their micro and macroeconomic environments. We prove the influence of the credit ratings, business cycle, estimated recovery rates and short-term interest rates on the utilization rates of a credit line. This model also provides risk measures such as Cash Flow-at-Risk and Stressed Cash Flow-at-Risk on credit portfolio using Monte Carlo simulations.(iii) Discussion on the Willingness-to-Pay (WTP) of an ambiguity neutral decision maker (DM) in order to reduce the risk in presence of ambiguity over probabilities. We show that the introduction of ambiguity through several ambiguity sources modifies the welfare level of all ambiguity-neutral and risk-averse DM when ambiguity and risk interact

In or around 2010, a nationwide reevaluation of the allowable properties for southern pine dimension lumber was initiated. This led to a 2013 reduction in the design values of visually graded southern pine dimension lumber and a resulting decrease in its commercial and utility value. This change compelled researchers and industry professionals to ponder what could be done to shore up the value of solid-sawn southern pine products going forward and potentially increase design values if appropriate. In pursuit of this question, this dissertation looks closely at three areas: 1) the possibility this reduction in mechanical performance is not merely limited to southern pine structural lumber but can also be observed in other solid-sawn softwood products and species, 2) flaws that might exist in commonly utilized statistical models for estimating allowable properties in lumber, and 3) the feasibility of using existing technologies to begin to compensate for the economic and/or utility losses attributed to the recent reduction in design values. This work is comprised of an introduction, a conclusion, and three independent content chapters utilizing a variety of statistical techniques to investigate whether strength and stiffness reduction might also be occurring in southern pine (and Douglasir) utility crossarms, evaluate the propriety of using a Weibull distribution model for estimating allowable properties in dimension lumber, and gauge the suitability of nondestructive testing methods for potentially identifying high-value premium grades in solid-sawn softwood products.

In this paper, we first present the basic principles of set theory and combinatorial analysis which are the most useful tools in computing probabilities. Then, we show some important properties derived from axioms of probability. Conditional probabilities come into play not only when some partial information is available, but also as a tool to compute probabilities more easily, even when partial information is unavailable. Then, the concept of random variable and its some related properties are introduced. For univariate random variables, we introduce the basic properties of some common discrete and continuous distributions. The important properties of jointly distributed random variables are also considered. Some inequalities, the law of large numbers and the central limit theorem are discussed. Finally, we introduce additional topics the Poisson process.