Submitted by Rafael Santana (rafael.silvasantana@ufpe.br) on 2017-04-19T18:10:57Z No. of bitstreams: 2 license_rdf: 1232 bytes, checksum: 66e71c371cc565284e70f40736c94386 (MD5) Dissertação_Versão Final.pdf: 1475057 bytes, checksum: 12f4f23219e2dd8cfd695075bb204ac4 (MD5) / Made available in DSpace on 2017-04-19T18:10:57Z (GMT). No. of bitstreams: 2 license_rdf: 1232 bytes, checksum: 66e71c371cc565284e70f40736c94386 (MD5) Dissertação_Versão Final.pdf: 1475057 bytes, checksum: 12f4f23219e2dd8cfd695075bb204ac4 (MD5) Previous issue date: 2016-08-23 / CAPES / Este trabalho trata de sistemas reparáveis que sofrem reparo imperfeito, utilizando uma classe de modelos de processos estocásticos conhecida como Processo de Renovação Generalizado (PRG), que é um modelo de idade virtual que determina a classificação do reparo de acordo com o grau de redução que este proporciona sob a idade real do equipamento, mensurada através de um parâmetro de rejuvenescimento, , e este modelo permite inserir uma maior flexibilidade quanto ao tratamento de dados de falhas. Foi proposto um modelo PRG com base na distribuição -Exponencial ( -PRG), onde o sucesso da Exponencial deve-se, em parte, à sua capacidade de exposições a caudas pesadas e fenômenos de lei de potência. Os estimadores de máxima verossimilhança não apresentaram expressões analíticas e, então, a estimação dos parâmetros -PRG foi realizada por meio do algoritmo evolucionário Differential Evolution (DE), que é algoritmo estocástico para resolver problemas de otimização global de funções não lineares, ou seja, é um método para minimizar funções não lineares e não diferenciáveis em um espaço contínuo de busca. Com base no método DE, foram realizadas simulações a partir de dados de falha extraídos da literatura. A partir das simulações executadas utilizando o método bootstrap paramétrico, mesmo existindo valores discrepantes, o processo de simulação manteve as características dos dados iniciais, de modo que informações sobre as falhas não foram perdidas. Com as simulações, concluiu-se que para tamanhos amostrais maiores, as abordagens bootstrap utilizadas tendem a fornecer estimativas intervalares semelhantes para os parâmetros -PRG. Além disso, foi possível obter alguns resultados estatísticos para os estimadores como a ausência de normalidade e estimar o parâmetro de rejuvenescimento do PRG. / This work deals with repairable systems that undergo imperfect repair, using a class of stochastic process models known as Generalized Renewal Process (GRP), which is a virtual age model that determines the classification of the repair according to the degree of reduction that This provides, under the real age of the equipment, measured through a rejuvenation parameter, , and this model allows to insert a greater flexibility in the treatment of data of failures. A GRP model was proposed based on the -Exponential distribution ( -GRP), where -Exponential success is due, in part, to its ability to expose heavy tails and power law phenomena. The maximum likelihood estimators did not present analytical expressions and, therefore, the estimation of the -GRP parameters was performed using the evolutionary algorithm Differential Evolution (DE), which is a stochastic algorithm to solve problems of global optimization of non-linear functions, that is, is a method to minimize non-linear and non-differentiable functions in a continuous search space. Based on the DE method, simulations were performed based on fault data extracted from the literature. From the simulations performed using the parametric bootstrap method, even if there were discrepant values, the simulation process maintained the characteristics of the initial data, so that information about the failures was not lost. With the simulations, it was concluded that for larger sample sizes, the bootstrap approaches used tend to provide similar interval estimates for the -GRP parameters. In addition, it was possible to obtain some statistical results for the estimators such as the absence of normality and to estimate the GRP rejuvenation parameter.

No description available.

The behavior of repairable equipment is often modeled under assumptions such as perfect repair, minimal repair, or negligible repair. However the majority of equipment behavior does not fall into any of these categories. Rather, repair actions do take time and the condition of equipment following repair is not strictly "as good as new" or "as bad as it was" prior to repair. Non-homogeneous processes that reflect this type of behavior are not studied nearly as much as the minimal repair case, but they far more realistic in many situations. For this reason, the quasi-renewal process provides an appealing alternative to many existing models for describing a non-homogeneous process. A quasi-renewal process is characterized by a parameter that indicates process deterioration or improvement by falling in the interval [0,1) or (1,Infinity) respectively. This parameter is the amount by which subsequent operation or repair intervals are scaled in terms of the immediately previous operation or repair interval. Two equivalent expressions for the point availability of a system with operation intervals and repair intervals that deteriorate according to a quasi-renewal process are constructed. In addition to general expressions for the point availability, several theoretical distributions on the operation and repair intervals are considered and specific forms of the quasi-renewal and point availability functions are developed. The two point availability expressions are used to provide upper and lower bounds on the approximated point availability. Numerical results and general behavior of the point availability and quasi-renewal functions are examined. The framework provided here allows for the description and prediction of the time-dependent behavior of a non-homogeneous process without the assumption of limiting behavior, a specific cost structure, or minimal repair. / Ph. D.

本研究以實質選擇權的觀點出發，針對高科技產業中各家競爭廠商投入R&D費用所研發出的創新技術與所對應的專利權進行評價。由於企業在競爭的環境中可藉由R&D過程獲取生產新商品所需的關鍵技術，進而申請專利權以保護公司的研發成果，提昇經營與獲利能力。然而，在技術上的小幅領先並不足以擺脫競爭對手的威脅而獲取絕大部分的市場商機，唯有競爭環境中的領導廠商成功地在技術上明顯的領先其競爭對手，方能取得該產品利基市場的獨占地位，獲取市場的絕大部分的潛在商機。針對高科技產業中不斷研發出來的創新技術所帶來的價值，本研究將以實質選擇權的觀點出發，評價此類創新技術所帶來的專利權之價值與此類研發投資所帶來的企業價值增值。 論文中將針對高資本支出、研發時間具有高度不確定性以及未來產品價格波動性高的高科技產業作為研究目標。定義在市場競爭下的個別公司必須藉由領先競爭環境內的所有對手多達兩代的創新技術方能取得市場的獨占地位。如此一來，企業一開始面對一個潛在的市場需求時，由於投入的研發費用將會影響企業的研發速度、市場獨占地位取得的可能性以及此投資案所能帶來的預期報酬，因此企業應針對此投資計畫決定投入多少研發預算，才能達到最大的預期報酬。

管制圖之經濟模型首由Duncan(1956)提出，自此之後陸續有學者致力研究經濟管制圖，包括X-bar管制圖、S管制圖等。但R管制圖之經濟設計目前尚無人提出。而在實務上，部份產業可能由於產品過於昂貴，或者產品的製造時間所需甚長，而使得品檢時所抽取的樣本數無法達到25個，這時若採用傳統的管制圖來分析製程，將無法顯示製程真正的狀態。因此本研究首先探討少量連串下X-bar和R管制圖之製作原理，並計算及整理出較完整的少量連串下X-bar和R的管制係數表。接著假設非機遇因素只影響製程運用Banerjee和Rahim(1987)的更新理論方法，建立少量連串情形下的R經濟管制圖。再利用最佳化方法，即可求得最適設計參數值。於是，少量連串情形下的R經濟管制圖得以建立。最後，我們將舉一個例子來說明如何獲得最適設計參數值、決定關鍵參數，以及少量連串情形下R經濟管制圖之建立與應用。

使用管制圖追蹤品質特性在製造過程中的變異前，使用者應先決定管制圖 的設計參數值 (Design Parameters) ， 如樣本大小、抽樣時間間隔，及 管制界限寬度等。當已知每次抽樣的樣本大小大於 10 ，且非隨機因素 (Assignable Causes) 的發生只會使製程變異增大時，則 S 管制圖應被 選用來追蹤製程是否穩定。 S 管制圖的經濟設計，首由 Collani 及 Sheil(1989) 提出，文中他們只考慮單一非隨機因素的情形。唯實務上， 製程常同時受多重非隨機困素的影響。為使製程模式假設更合理，使用更 有彈性，我們先將多重非隨機因素製程表示為更新過程 (Renewal Processes) ， 其中每個更新循環 (Renewal Cycles) 則表示為馬可夫過 程 (Markov Process) 。 接著，以 S 管制圖追蹤的製程平均循環時間 (The Expected Cycle Time) 及平均循環成本 (The Expected Cycle Cost)應用馬可夫性質可容易的推導出。最後，目標函數可利用更新報酬 過程 (Renewal Reward Processes) 性質獲得。 由於目標函數是設計參 數之函數， 因此藉著最佳化目標函數， S管制圖之最適設計參數值可被 決定。由針對一個特例所做的變異數分析及回應圖分析結果，我們可決定 重要製程與成本參數，這些參數的了解可做為決策者決策上的參考。另外 ， S 經濟管制圖所發生的品質成本遠比傳統 S 管制圖的小,而在製程失 控下， S 經濟管制圖的偵測力也比傳統 S 管制圖的強。 是以 S 經濟管 制圖優於傳統的 S 管制圖。本研究所推導出的製程模式及 S 管制圖設 計方法可應用於各種分配的製程變數 (Process Variable) 及其他類型管 制圖的設計上。

The aim of this thesis is to develop algorithmic methods for computing particular performance measures of interest for a general class of discrete-based insurance risk models. We build upon and generalize the insurance risk models considered by Drekic and Mera (2011) and Alfa and Drekic (2007), by incorporating a threshold-based dividend system in which dividends only get paid provided some period of good financial health is sustained above a pre-specified threshold level. We employ two fundamental methods for calculating the performance measures under the more general framework. The first method adopts the matrix-analytic approach originally used by Alfa and Drekic (2007) to calculate various ruin-related probabilities of interest such as the trivariate distribution of the time of ruin, the surplus prior to ruin, and the deficit at ruin. Specifically, we begin by introducing a particular trivariate Markov process and then expressing its transition probability matrix in a block-matrix form. From this characterization, we next identify an initial probability vector for the process, from which certain important conditional probability vectors are defined. For these vectors to be computed efficiently, we derive recursive expressions for each of them. Subsequently, using these probability vectors, we derive expressions which enable the calculation of conditional ruin probabilities and, from which, their unconditional counterparts naturally follow. The second method used involves the first claim conditioning approach (i.e., condition on knowing the time the first claim occurs and its size) employed in many ruin theoretic articles including Drekic and Mera (2011). We derive expressions for the finite-ruin time based Gerber-Shiu function as well as the moments of the total dividends paid by a finite time horizon or before ruin occurs, whichever happens first. It turns out that both functions can be expressed in elegant, albeit long, recursive formulas. With the algorithmic derivations obtained from the two fundamental methods, we next focus on computational aspects of the model class by comparing six different types of models belonging to this class and providing numerical calculations for several parametric examples, highlighting the robustness and versatility of our model class. Finally, we identify several potential areas for future research and possible ways to optimize numerical calculations.

The aim of this thesis is to develop algorithmic methods for computing particular performance measures of interest for a general class of discrete-based insurance risk models. We build upon and generalize the insurance risk models considered by Drekic and Mera (2011) and Alfa and Drekic (2007), by incorporating a threshold-based dividend system in which dividends only get paid provided some period of good financial health is sustained above a pre-specified threshold level. We employ two fundamental methods for calculating the performance measures under the more general framework. The first method adopts the matrix-analytic approach originally used by Alfa and Drekic (2007) to calculate various ruin-related probabilities of interest such as the trivariate distribution of the time of ruin, the surplus prior to ruin, and the deficit at ruin. Specifically, we begin by introducing a particular trivariate Markov process and then expressing its transition probability matrix in a block-matrix form. From this characterization, we next identify an initial probability vector for the process, from which certain important conditional probability vectors are defined. For these vectors to be computed efficiently, we derive recursive expressions for each of them. Subsequently, using these probability vectors, we derive expressions which enable the calculation of conditional ruin probabilities and, from which, their unconditional counterparts naturally follow. The second method used involves the first claim conditioning approach (i.e., condition on knowing the time the first claim occurs and its size) employed in many ruin theoretic articles including Drekic and Mera (2011). We derive expressions for the finite-ruin time based Gerber-Shiu function as well as the moments of the total dividends paid by a finite time horizon or before ruin occurs, whichever happens first. It turns out that both functions can be expressed in elegant, albeit long, recursive formulas. With the algorithmic derivations obtained from the two fundamental methods, we next focus on computational aspects of the model class by comparing six different types of models belonging to this class and providing numerical calculations for several parametric examples, highlighting the robustness and versatility of our model class. Finally, we identify several potential areas for future research and possible ways to optimize numerical calculations.

Pour V un processus aléatoire càd-làg, on appelle diffusion dans le milieu aléatoire V la solution formelle de l’équation différentielle stochastique \[ dX_t = - \frac1{2} V'(X_t) dt + dB_t, \] où B est un mouvement brownien indépendant de V . Le temps local au temps t et à la position x dela diffusion, noté LX(t, x), donne une mesure de la quantité de temps passé par la diffusion au point x, avant l’instant t. Dans cette thèse nous considérons le cas où le milieu V est un processus de Lévyspectralement négatif convergeant presque sûrement vers −∞, et nous nous intéressons au comportementasymptotique lorsque t tend vers l’infini de $\mathcal{L}_X^*(t) := \sup_{\mathbb{R}} \mathcal{L}_X(t, .)$ le supremum du temps local de ladiffusion, ainsi qu’à la localisation du point le plus visité par la diffusion. Nous déterminons notammentla convergence en loi et le comportement presque sûr du supremum du temps local. Cette étude révèleque le comportement asymptotique du supremum du temps local est fortement lié aux propriétés desfonctionnelles exponentielles des processus de Lévy conditionnés à rester positifs et cela nous amène àétudier ces dernières. Si V est un processus de Lévy, V ↑ désigne le processus V conditionné à rester positif.La fonctionnelle exponentielle de V ↑ est la variable aléatoire $\int_0^{+ \infty} e^{- V^{\uparrow} (t)}dt$ . Nous étudions en particulier sa finitude, son auto-décomposabilité, l’existence de moments exponentiels, sa queue en 0, l’existence et larégularité de sa densité. / For V a random càd-làg process, we call diffusion in the random medium V the formal solution of thestochastic differential equation \[ dX_t = - \frac1{2} V'(X_t) dt + dB_t, \] where B is a brownian motion independent of V . The local time at time t and at the position x of thediffusion, denoted by LX(t, x), gives a measure of the amount of time spent by the diffusion at point x,before instant t. In this thesis we consider the case where the medium V is a spectrally negative Lévyprocess converging almost surely toward −∞, and we are interested in the asymptotic behavior, whent goes to infinity, of $\mathcal{L}_X^*(t) := \sup_{\mathbb{R}} \mathcal{L}_X(t, .)$ the supremum of the local time of the diffusion. We arealso interested in the localization of the point most visited by the diffusion. We notably establish theconvergence in distribution and the almost sure behavior of the supremum of the local time. This studyreveals that the asymptotic behavior of the supremum of the local time is deeply linked to the propertiesof the exponential functionals of Lévy processes conditioned to stay positive and this brings us to studythem. If V is a Lévy process, V ↑ denotes the process V conditioned to stay positive. The exponentialfunctional of V ↑ is the random variable $\int_0^{+ \infty} e^{- V^{\uparrow} (t)}dt$ . For this object, we study in particular finiteness,

Submitted by Fabio Sobreira Campos da Costa (fabio.sobreira@ufpe.br) on 2016-08-05T13:45:36Z No. of bitstreams: 2 license_rdf: 1232 bytes, checksum: 66e71c371cc565284e70f40736c94386 (MD5) 2016 02 Dissertação V18.pdf: 847550 bytes, checksum: b3b34305dd3687f0d1a2e2aa1a8ef506 (MD5) / Made available in DSpace on 2016-08-05T13:45:36Z (GMT). No. of bitstreams: 2 license_rdf: 1232 bytes, checksum: 66e71c371cc565284e70f40736c94386 (MD5) 2016 02 Dissertação V18.pdf: 847550 bytes, checksum: b3b34305dd3687f0d1a2e2aa1a8ef506 (MD5) Previous issue date: 2016-02-19 / CAPEs / A terceirização da manutenção e a adesão da garantia estendida para equipamentos hospitalares tem se tornado uma tendência ao longo das últimas décadas, pois estão relacionadas com a crescente complexidade e modernização dos dispositivos médicos, bem como, com a recorrente prática da exclusividade do fabricante na realização da manutenção. Geralmente, o relacionamento entre a instituição de saúde e o fabricante é conduzido por meio de um documento, especificando questões como: nível de confiabilidade, desempenho operacional, disponibilidade, duração da garantia, preço da manutenção, penalidades e a política de manutenção a ser implementada. Sendo assim, a presente dissertação estuda quantitativamente o problema de garantia estendida para equipamentos hospitalares, por meio da junção de duas ferramentas: o jogo de Stackelberg, designado para estruturar a forma de relacionamento entre as empresas, e o Processo de Renovação Generalizado, responsável processo de falha – reparo do equipamento (reparo imperfeito). Um cenário foi criado para a aplicação de tais métodos. Inicialmente, o fabricante ao vender um equipamento hospitalar também oferece duas possibilidades para a execução da manutenção: a primeira, garantia estendida, e a segunda, serviço sob demanda. Posteriormente, a decisão do hospital é influenciada pela estrutura de preços imposta do fabricante, a confiabilidade do equipamento e o seu grau de aversão ao risco, visto que as falhas do dispositivo são eventos aleatórios. Para ilustrar tal situação, realiza-se um exemplo numérico com dados de falha e reparo de um Angiográfo. O equilíbrio do modelo implica na maximização do lucro esperado do fabricante e o hospital decidindo pela adesão da garantia estendida. Adicionalmente, comparando as soluções do reparo imperfeito com os cenários de reparos perfeito e mínimo, observou-se similaridade nas estratégias para os casos de reparos imperfeito e perfeito, enquanto que, na relação entre os reparos imperfeito e mínimo as estratégias darse- ão de maneira oposta. Finalmente, o lucro esperado do fabricante diminui conforme aumenta o número médio de falhas. / The outsourcing of maintenance and the acquisition of extended warranty for hospital equipment has become a trend over the past few decades, since they are related to the growing complexity, modernization of medical devices and the recurring practice of the manufacturer's exclusivity in performing maintenance services. Generally, the relationship between the health institution and the manufacturer is conducted through a document specifying the following issues: level of reliability, operating performance, availability, warranty period, maintenance price, penalties and maintenance policy to be implemented. Under these circumstances, this thesis analyzes the problem of the extended warranty for clinical equipment by joining two tools: the Stackelberg game, designed to model the relation between companies and the Generalized Renewal Process, employed for modeling failure-repair process (imperfect repair). A scenario was created for the application of such methods. Initially, the manufacturer intends to sell a medical equipment and also offers two maintenance possibilities: first, an extended warranty, and second, maintenance services on demand. Subsequently, the hospital's decision is influenced by manufacturer's price structure, equipment reliability and the degree of risk aversion, since the failures occurrences of the device are random events. To illustrate this situation, an application example with failure and repair data of an Angiography equipment is presented. The equilibrium of model implies in expected profit maximization for the manufacturer and hospital chooses the extended warranty option. In addition, by comparing the solutions of the imperfect repair with perfect and minimal repair scenarios, a similarity in the strategies adopted in cases of imperfect and perfect repairs was observed, while the strategies were opposite when comparing imperfect and minimal repairs. Finally, the expected profit of the manufacturer decreases as the average number of failures increases.