Distribuição de funções de variáveis aleatórias dependentes e R-Vines cópulas

Dissertação (mestrado)—Universidade de Brasília, Instituto de Ciências Exatas, Departamento de Estatística, 2015.

Aplicação da teoria das opções reais na análise de investimentos em concessão florestal

Dissertação (mestrado)—Universidade de Brasília, Faculdade de Tecnologia, Departamento de Engenharia Florestal, 2016.

Hypothesis test for changes in variance using a statistic based in P-values in a time series of normal independent observations.

The present work proposes a Hypothesis Test to detect a shift in the variance of a series of independent normal observations using a statistic based on the p-values of the F distribution. Since the probability distribution function of this statistic is intractable, critical values were we estimated numerically through extensive simulation. A regression approach was used to simplify the quantile evaluation and extrapolation. The power of the test was simulated using Monte Carlo simulation, and the results were compared with the Chen test (1997) to prove its efficiency. Time series analysts might find the test useful to address homoscedasticity studies were at most one change might be involved.

New search for the Neutron Electric Dipole Moment using ultracold neutrons at the Spallation Neutron Source

This document introduces the planned new search for the neutron Electric Dipole Moment at the Spallation Neutron Source at the Oak Ridge National Laboratory. A spin precession measurement is to be carried out using Ultracold neutrons diluted in a superfluid Helium bath at T = 0.5 K, where spin polarized 3He atoms act as detector of the neutron spin polarization. This manuscript describes some of the key aspects of the planned experiment with the contributions from Caltech to the development of the project.

Techniques used in the design of magnet coils for Nuclear Magnetic Resonance were adapted to the geometry of the experiment. Described is an initial design approach using a pair of coils tuned to shield outer conductive elements from resistive heat loads, while inducing an oscillating field in the measurement volume. A small prototype was constructed to test the model of the field at room temperature.

A large scale test of the high voltage system was carried out in a collaborative effort at the Los Alamos National Laboratory. The application and amplification of high voltage to polished steel electrodes immersed in a superfluid Helium bath was studied, as well as the electrical breakdown properties of the electrodes at low temperatures. A suite of Monte Carlo simulation software tools to model the interaction of neutrons, 3He atoms, and their spins with the experimental magnetic and electric fields was developed and implemented to further the study of expected systematic effects of the measurement, with particular focus on the false Electric Dipole Moment induced by a Geometric Phase akin to Berry’s phase.

An analysis framework was developed and implemented using unbinned likelihood to fit the time modulated signal expected from the measurement data. A collaborative Monte Carlo data set was used to test the analysis methods.

What Transaction Costs are Acceptable in Life Insurance Products from the Policyholders' Viewpoint?

Purpose - The purpose of this paper is to analyze what transaction costs are acceptable for customers in different investments. In this study, two life insurance contracts, a mutual fund and a risk-free investment, as alternative investment forms are considered. The first two products under scrutiny are a life insurance investment with a point-to-point capital guarantee and a participating contract with an annual interest rate guarantee and participation in the insurer's surplus. The policyholder assesses the various investment opportunities using different utility measures. For selected types of risk profiles, the utility position and the investor's preference for the various investments are assessed. Based on this analysis, the authors study which cost levels can make all of the products equally rewarding for the investor. Design/methodology/approach - The paper notes the risk-neutral valuation calibration using empirical data utility and performance measurement dynamics underlying: geometric Brownian motion numerical examples via Monte Carlo simulation. Findings - In the first step, the financial performance of the various saving opportunities under different assumptions of the investor's utility measurement is studied. In the second step, the authors calculate the level of transaction costs that are allowed in the various products to make all of the investment opportunities equally rewarding from the investor's point of view. A comparison of these results with transaction costs that are common in the market shows that insurance companies must be careful with respect to the level of transaction costs that they pass on to their customers to provide attractive payoff distributions. Originality/value - To the best of the authors' knowledge, their research question - i.e. which transaction costs for life insurance products would be acceptable from the customer's point of view - has not been studied in the above described context so far.

Produção de pellets de madeira no Brasil : estratégia, custo e risco do investimento

Tese (doutorado)—Universidade de Brasília, Faculdade de Tecnologia, Departamento de Engenharia Florestal, Programa de Pós-Graduação em Ciências Florestais, 2015.

Implementação de um modelo de erosão para a simulação de carreiras dos Oficiais da Marinha Portuguesa

Em outubro de 2012, a Direção de Análise e Gestão da Informação (DAGI), em colaboração com a Superintendência do Pessoal (SP) e Direção do Pessoal (DP), iniciou o desenvolvimento de um protótipo de simulador, que designou por “Protótipo Fluxo de Carreiras”. Este simulador permite parametrizar diversos fatores que condicionam o desenvolvimento de carreira dos militares e que estão associados a mecanismos reguladores de carreira que se encontram vertidos no Estatuto dos Militares das Forças Armadas (EMFAR). Para cada ano do período de simulação, a situação de cada militar de uma determinada classe é atualizada e são verificadas as condições para a ocorrência de promoções e passagens à reserva. O evento “passagem à reserva” de um militar pode ter origem em regras determinísticas (exemplo: militar atinge a idade limite de passagem à reserva no seu posto) ou em condições estocásticas ou aleatórias (exemplos: óbito, exclusão da promoção, requerer voluntariamente a passagem à reserva, etc.). Estas últimas situações resultam do fenómeno de erosão dos quadros que pode ser observado a partir do histórico de saídas desta natureza. Até 2015, o simulador de carreiras não comtemplava um modelo de erosão, pelo que os resultados disponibilizados (indicadores de fluxo de carreira) dependiam exclusivamente de mecanismos determinísticos. Desta forma estes resultados apresentam uma natureza “pessimista” e com fraca aderência à realidade. O presente trabalho tem como objetivo construir um modelo descritivo da erosãodos militares oficiais da Marinha, tendo por base dados de saídas (excetuando saídas relacionadas com regras determinísticas previstas no EMFAR) no período de 2008 a2015. Para cada classe da categoria de oficiais é estimada uma função de probabilidadecondicional ao tempo de serviço efetivo ou à idade do militar que representa apropensão para um militar sair do quadro antes de ser verificada uma condição determinística. Estas funções foram integradas no simulador de carreiras para que os resultados possam reproduzir a componente de erosão. Usando o método de simulação de Monte Carlo é possível obter a distribuição dos indicadores de fluxo de carreira. Porfim, objetiva-se realizar uma comparação entre uma simulação com fatores estocásticos (com erosão) e uma simulação considerando apenas fatores determinísticos (semerosão). Este trabalho visa refletir o panorama atual da erosão de pessoal na Marinha, permitindo assim melhorar a qualidade das previsões de efetivos ao longo do tempo bem como aumentar a capacidade de intervenção e resposta na identificação e correção antecipada de possíveis estruturações.

Age-Dependent Fragility and Life-Cycle Cost Analysis of Timber and Steel Distribution Poles Subjected to Hurricanes

Power distribution systems are susceptible to extreme damage from natural hazards especially hurricanes. Hurricane winds can knock down distribution poles thereby causing damage to the system and power outages which can result in millions of dollars in lost revenue and restoration costs. Timber has been the dominant material used to support overhead lines in distribution systems. Recently however, utility companies have been searching for a cost-effective alternative to timber poles due to environmental concerns, durability, high cost of maintenance and need for improved aesthetics. Steel has emerged as a viable alternative to timber due to its advantages such as relatively lower maintenance cost, light weight, consistent performance, and invulnerability to wood-pecker attacks. Both timber and steel poles are prone to deterioration over time due to decay in the timber and corrosion of the steel. This research proposes a framework for conducting fragility analysis of timber and steel poles subjected to hurricane winds considering deterioration of the poles over time. Monte Carlo simulation was used to develop the fragility curves considering uncertainties in strength, geometry and wind loads. A framework for life-cycle cost analysis is also proposed to compare the steel and timber poles. The results show that steel poles can have superior reliability and lower life-cycle cost compared to timber poles, which makes them suitable substitutes.

Study on Bivariate Normal Distribution

Let (X, Y) be bivariate normal random vectors which represent the responses as a result of Treatment 1 and Treatment 2. The statistical inference about the bivariate normal distribution parameters involving missing data with both treatment samples is considered. Assuming the correlation coefficient ρ of the bivariate population is known, the MLE of population means and variance (ξ, η, and σ2) are obtained. Inferences about these parameters are presented. Procedures of constructing confidence interval for the difference of population means ξ – η and testing hypothesis about ξ – η are established. The performances of the new estimators and testing procedure are compared numerically with the method proposed in Looney and Jones (2003) on the basis of extensive Monte Carlo simulation. Simulation studies indicate that the testing power of the method proposed in this thesis study is higher.

Power Study on Testing Epidemic Alternatives

Detecting change points in epidemic models has been studied by many scholars. Yao (1993) summarized five existing test statistics in the literature. Out of those test statistics, it was observed that the likelihood ratio statistic showed its standout power. However, all of the existing test statistics are based on an assumption that population variance is known, which is an unrealistic assumption in practice. To avoid assuming known population variance, a new test statistic for detecting epidemic models is studied in this thesis. The new test statistic is a parameter-free test statistic which is more powerful compared to the existing test statistics. Different sample sizes and lengths of epidemic durations are used for the power comparison purpose. Monte Carlo simulation is used to find the critical values of the new test statistic and to perform the power comparison. Based on the Monte Carlo simulation result, it can be concluded that the sample size and the length of the duration have some effect on the power of the tests. It can also be observed that the new test statistic studied in this thesis has higher power than the existing test statistics do in all of cases.

Inferences about Parameters of Trivariate Normal Distribution with Missing Data

Multivariate normal distribution is commonly encountered in any field, a frequent issue is the missing values in practice. The purpose of this research was to estimate the parameters in three-dimensional covariance permutation-symmetric normal distribution with complete data and all possible patterns of incomplete data. In this study, MLE with missing data were derived, and the properties of the MLE as well as the sampling distributions were obtained. A Monte Carlo simulation study was used to evaluate the performance of the considered estimators for both cases when ρ was known and unknown. All results indicated that, compared to estimators in the case of omitting observations with missing data, the estimators derived in this article led to better performance. Furthermore, when ρ was unknown, using the estimate of ρ would lead to the same conclusion.

Effects of truck traffic on top-down fatigue cracking performance of flexible pavements using a new mechanics-based analysis framework

The mechanics-based analysis framework predicts top-down fatigue cracking initiation time in asphalt concrete pavements by utilising fracture mechanics and mixture morphology-based property. To reduce the level of complexity involved, traffic data were characterised and incorporated into the framework using the equivalent single axle load (ESAL) approach. There is a concern that this kind of simplistic traffic characterisation might result in erroneous performance predictions and pavement structural designs. This paper integrates axle load spectra and other traffic characterisation parameters into the mechanics-based analysis framework and studies the impact these traffic characterisation parameters have on predicted fatigue cracking performance. The traffic characterisation inputs studied are traffic growth rate, axle load spectra, lateral wheel wander and volume adjustment factors. For this purpose, a traffic integration approach which incorporates Monte Carlo simulation and representative traffic characterisation inputs was developed. The significance of these traffic characterisation parameters was established by evaluating a number of field pavement sections. It is evident from the results that all the traffic characterisation parameters except truck wheel wander have been observed to have significant influence on predicted top-down fatigue cracking performance.

The Power of the Synthetic Control Method

The synthetic control method (SCM) is a new, popular method developed for the purpose of estimating the effect of an intervention when only one single unit has been exposed. Other similar, unexposed units are combined into a synthetic control unit intended to mimic the evolution in the exposed unit, had it not been subject to exposure. As the inference relies on only a single observational unit, the statistical inferential issue is a challenge. In this paper, we examine the statistical properties of the estimator, study a number of features potentially yielding uncertainty in the estimator, discuss the rationale for statistical inference in relation to SCM, and provide a Web-app for researchers to aid in their decision of whether SCM is powerful for a specific case study. We conclude that SCM is powerful with a limited number of controls in the donor pool and a fairly short pre-intervention time period. This holds as long as the parameter of interest is a parametric specification of the intervention effect, and the duration of post-intervention period is reasonably long, and the fit of the synthetic control unit to the exposed unit in the pre-intervention period is good.

Demography of a deep-sea lantern shark (Etmopterus spinax) caught in trawl fisheries of the northeastern Atlantic: Application of Leslie matrices with incorporated uncertainties

The deep-sea lantern shark Etmopterus spinax occurs in the northeast Atlantic on or near the bottoms of the outer continental shelves and slopes, and is regularly captured as bycatch in deep-water commercial fisheries. Given the lack of knowledge on the impacts of fisheries on this species, a demographic analysis using age-based Leslie matrices was carried out. Given the uncertainties in the mortality estimates and in the available life history parameters, several different scenarios, some incorporating stochasticity in the life history parameters (using Monte Carlo simulation), were analyzed. If only natural mortality were considered, even after introducing uncertainties in all parameters, the estimated population growth rate (A) suggested an increasing population. However, if fishing mortality from trawl fisheries is considered, the estimates of A either indicated increasing or declining populations. In these latter cases, the uncertainties in the species reproductive cycle seemed to be particularly relevant, as a 2-year reproductive cycle indicated a stable population, while a longer (3-year cycle) indicated a declining population. The estimated matrix elasticities were in general higher for the survivorship parameters of the younger age classes and tended to decrease for the older ages. This highlights the susceptibility of this deep-sea squaloid to increasing fishing mortality, emphasizing that even though this is a small-sized species, it shows population dynamics patterns more typical of the larger-sized and in general more vulnerable species. (C) 2014 Elsevier Ltd. All rights reserved.

Simulation of default events in a CDX and estimation of the spread

The portfolio generating the iTraxx EUR index is modeled by coupled Markov chains. Each of the industries of the portfolio evolves according to its own Markov transition matrix. Using a variant of the method of moments, the model parameters are estimated from a data set of Standard and Poor's. Swap spreads are evaluated by Monte-Carlo simulations. Along with an actuarially fair spread, at least squares spread is considered.