No description available.

Extreme value theory (EVT) has wide applicability in several areas like hydrology, engineering, science and finance. Across the world, we can see the disruptive effects of flooding, due to heavy rains or storms. Many countries in the world are suffering from natural disasters like heavy rains, storms, floods, and also higher temperatures leading to desertification. One of the best known extraordinary natural disasters is the 1931 Huang He flood, which led to around 4 millions deaths in China; these were a series of floods between Jul and Nov in 1931 in the Huang He river.Several publications are focused on how to find the best model for these events, and to predict the behaviour of these events. Normal, log-normal, Gumbel, Weibull, Pearson type, 4-parameter Kappa, Wakeby and GEV distributions are presented as statistical models for extreme events. However, GEV and GP distributions seem to be the most widely used models for extreme events. In spite of that, these models have been misused as models for extreme values in many areas.The aim of this dissertation is to create new modifications of univariate extreme value models.The modifications developed in this dissertation are divided into two parts: in the first part, we make generalisations of GEV and GP, referred to as the Kumaraswamy GEV and Kumaraswamy GP distributions. The major benefit of these models is their ability to fit the skewed data better than other models. The other idea in this study comes from Chen, which is presented in Proceedings of the International Conference on Computational Intelligence and Software Engineering, pp. 1-4. However, the cumulative and probability density functions for this distribution do not appear to be valid functions. The correction of this model is presented in chapter 6.The major problem in extreme event models is the ability of the model to fit tails of data. In chapter 7, the idea of the Chen model with the correction is combined with the GEV distribution to introduce a new model for extreme values referred to as new extreme value (NEV) distribution. It seems to be more flexible than the GEV distribution.

Submitted by Divisão de Documentação/BC Biblioteca Central (ddbc@ufam.edu.br) on 2018-05-22T13:53:20Z No. of bitstreams: 2 license_rdf: 0 bytes, checksum: d41d8cd98f00b204e9800998ecf8427e (MD5) versaofinal.pdf: 8756608 bytes, checksum: e4b5f21e17776e8f9af04b6752317a59 (MD5) / Approved for entry into archive by Divisão de Documentação/BC Biblioteca Central (ddbc@ufam.edu.br) on 2018-05-22T14:16:29Z (GMT) No. of bitstreams: 2 license_rdf: 0 bytes, checksum: d41d8cd98f00b204e9800998ecf8427e (MD5) versaofinal.pdf: 8756608 bytes, checksum: e4b5f21e17776e8f9af04b6752317a59 (MD5) / Made available in DSpace on 2018-05-22T14:16:29Z (GMT). No. of bitstreams: 2 license_rdf: 0 bytes, checksum: d41d8cd98f00b204e9800998ecf8427e (MD5) versaofinal.pdf: 8756608 bytes, checksum: e4b5f21e17776e8f9af04b6752317a59 (MD5) Previous issue date: 2018-03-09 / CAPES - Coordenação de Aperfeiçoamento de Pessoal de Nível Superior / Relative humidity interferes in many aspects in the life of the human being, and due to the many consequences that a low or a high percentage can entail, the control of its level is of paramount importance. Thus, the modeling of extreme situations of this variable can aid in the planning of human activities that are susceptible to their harmful effects, such as public health. The main interest is to predict, based on probability density functions applied to observed data, the values that may occur in a certain locality. The Generalized Distribution of Extreme Values has been widely used for this purpose and research using Time Series analysis of meteorological and climatic data. In this work, a statistical model is proposed for prediction of rates and temporal proportions and/or spatially dependents. The model was constructed by marginalizing the Kumaraswamy G-exponentialised distribution conditioned to a random field with positive alpha-stable distribution. Some properties of this model were presented, procedures for estimation and inference were discussed and an MCEM algorithm was developed to estimate the parameters. As a particular case, the model was used for spatial prediction of relative humidity in weather stations at Amazonas state, Brazil. / A umidade relativa interfere em vários aspectos na vida do ser humano, e devido as muitas consequências que um baixo ou um alto percentual podem acarretar, o controle de seu nível é de suma importância. Dessa forma, a modelagem de situações extremas dessa variável pode auxiliar no planejamento de atividades humanas que sejam suscetíveis aos seus efeitos danosos, como a saúde pública. O principal interesse é prever com base em funções densidade de probabilidade aplicadas aos dados observados, os valores que possam ocorrer em uma certa localidade. A distribuição Generalizada de Valores Extremos tem sido amplamente utilizada com essa finalidade e pesquisas utilizando análise de Séries Temporais de dados meteorológicos e climáticos. Neste trabalho, é proposto um modelo estatístico para predição de taxas e proporções temporais e/ou espacialmente dependentes. O modelo foi construído através da marginalização da distribuição Kumaraswamy G-exponencializada condicionada a um campo aleatório com distribuição alfaestável positivo. Algumas propriedades desse modelo foram apresentadas, procedimentos para estimação e inferência foram discutidos e um algoritmo MCEM foi desenvolvido parar estimar os parâmetros. Como um caso particular, o modelo foi utilizado para predição espacial da umidade relativa do ar observada nas estações meteorológicas do Estado do Amazonas.