Testes cosmológicos aplicados a modelos de energia escura

A significant observational effort has been directed to investigate the nature of the so-called dark energy. In this dissertation we derive constraints on dark energy models using three different observable: measurements of the Hubble rate H(z) (compiled by Meng et al. in 2015.); distance modulus of 580 Supernovae Type Ia (Union catalog Compilation 2.1, 2011); and the observations of baryon acoustic oscilations (BAO) and the cosmic microwave background (CMB) by using the so-called CMB/BAO of six peaks of BAO (a peak determined through the Survey 6dFGS data, two through the SDSS and three through WiggleZ). The statistical analysis used was the method of the χ2 minimum (marginalized or minimized over h whenever possible) to link the cosmological parameter: m, ω and δω0. These tests were applied in two parameterization of the parameter ω of the equation of state of dark energy, p = ωρ (here, p is the pressure and ρ is the component of energy density). In one, ω is considered constant and less than -1/3, known as XCDM model; in the other the parameter of state equantion varies with the redshift, where we the call model GS. This last model is based on arguments that arise from the theory of cosmological inflation. For comparison it was also made the analysis of model CDM. Comparison of cosmological models with different observations lead to different optimal settings. Thus, to classify the observational viability of different theoretical models we use two criteria information, the Bayesian information criterion (BIC) and the Akaike information criteria (AIC). The Fisher matrix tool was incorporated into our testing to provide us with the uncertainty of the parameters of each theoretical model. We found that the complementarity of tests is necessary inorder we do not have degenerate parametric spaces. Making the minimization process we found (68%), for the Model XCDM the best fit parameters are m = 0.28 ± 0, 012 and ωX = −1.01 ± 0, 052. While for Model GS the best settings are m = 0.28 ± 0, 011 and δω0 = 0.00 ± 0, 059. Performing a marginalization we found (68%), for the Model XCDM the best fit parameters are m = 0.28 ± 0, 012 and ωX = −1.01 ± 0, 052. While for Model GS the best settings are M = 0.28 ± 0, 011 and δω0 = 0.00 ± 0, 059.

Avaliação e correções de testes de hipóteses em modelos de sobrevivência com fração de cura

Survival models deals with the modelling of time to event data. In certain situations, a share of the population can no longer be subjected to the event occurrence. In this context, the cure fraction models emerged. Among the models that incorporate a fraction of cured one of the most known is the promotion time model. In the present study we discuss hypothesis testing in the promotion time model with Weibull distribution for the failure times of susceptible individuals. Hypothesis testing in this model may be performed based on likelihood ratio, gradient, score or Wald statistics. The critical values are obtained from asymptotic approximations, which may result in size distortions in nite sample sizes. This study proposes bootstrap corrections to the aforementioned tests and Bartlett bootstrap to the likelihood ratio statistic in Weibull promotion time model. Using Monte Carlo simulations we compared the nite sample performances of the proposed corrections in contrast with the usual tests. The numerical evidence favors the proposed corrected tests. At the end of the work an empirical application is presented.

Modelos flexíveis de sobrevivência com fração de cura: implementação computacional

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Efeito de diferentes divisões territoriais na flutuação aleatória de indicadores socioeconômicos relacionados à determinação social da saúde

This research aimed to analyse the effect of different territorial divisions in the random fluctuation of socio-economic indicators related to social determinants of health. This is an ecological study resulting from a combination of statistical methods including individuated and aggregate data analysis, using five databases derived from the database of the Brazilian demographic census 2010: overall results of the sample by weighting area. These data were grouped into the following levels: households; weighting areas; cities; Immediate Urban Associated Regions and Intermediate Urban Associated Regions. A theoretical model related to social determinants of health was used, with the dependent variable Household with death and as independent variables: Black race; Income; Childcare and school no attendance; Illiteracy; and Low schooling. The data was analysed in a model related to social determinants of health, using Poisson regression in individual basis, multilevel Poisson regression and multiple linear regression in light of the theoretical framework of the area. It was identified a greater proportion of households with deaths among those with at least one black resident, lower-income, illiterate, who do not attend or attended school or day-care and less educated. The analysis of the adjusted model showed that most adjusted prevalence ratio was related to Income, where there is a risk value of 1.33 for households with at least one resident with lower average personal income to R$ 655,00 (Brazilian current). The multilevel analysis demonstrated that there was a context effect when the variables were subjected to the effects of areas, insofar as the random effects were significant for all models and with different prevalence rates being higher in the areas with smaller dimensions - Weighting areas with coefficient of 0.035 and Cities with coefficient of 0.024. The ecological analyses have shown that the variable Income and Low schooling presented explanatory potential for the outcome on all models, having income greater power to determine the household deaths, especially in models related to Immediate Urban Associated Regions with a standardized coefficient of -0.616 and regions intermediate urban associated regions with a standardized coefficient of -0.618. It was concluded that there was a context effect on the random fluctuation of the socioeconomic indicators related to social determinants of health. This effect was explained by the characteristics of territorial divisions and individuals who live or work there. Context effects were better identified in the areas with smaller dimensions, which are more favourable to explain phenomena related to social determinants of health, especially in studies of societies marked by social inequalities. The composition effects were better identified in the Regions of Urban Articulation, shaped through mechanisms similar to the phenomenon under study.

Modelos em provisão de sinistros

Part of the work of an insurance company is to keep claims reserves, which is known as the technical reserves, in order to mitigate the risk inherent in their activities and comply with the legal obligations. There are several methods for estimate the claims reserves, deterministics and stochastics methods. One of the most used method is the deterministic method Chain Ladder, of simple application. However, the deterministics methods produce only point estimates, for which the stochastics methods have become increasingly popular because they are capable of producing interval estimates, measuring the variability inherent in the technical reserves. In this study the deterministics methods (Grossing Up, Link Ratio and Chain Ladder) and stochastics (Thomas Mack and Bootstrap associated with Overdispersed Poisson model) will be applied to estimate the claims reserves derived from automobile material damage occurred until December 2012. The data used in this research is based on a real database provided by AXA Portugal. The comparison of results obtained by different methods is hereby presented.

Algumas aplicações da Estatística na área de Economia e Gestão

"[…]. A aplicação de técnicas estatísticas na análise de problemas económicos, em que é necessário testar hipóteses sobre as relações económicas e prever mudanças nos valores de variáveis relevantes, tem tido uma importância crescente. Algumas relações teóricas entre variáveis económicas podem ser expressas usando modelos matemáticos, cujos parâmetros podem ser estimados usando métodos estatísticos. […].Os gestores de empresas são frequentemente confrontados com processos de tomada de decisão, pelo que a posse de conhecimentos de Estatística e o domínio de software que permita a gestão de informação em tempo real é uma mais-valia, principalmente na análise de situações que incluam cenários de incerteza. Nessa perspetiva, os gestores e todos os outros tomadores de decisão têm de ser capazes de entender a informação e usá-la eficazmente, não esquecendo que “se gerir é tomar decisões, gerir bem é tomar boas decisões".

Otimização da extração de ergosterol assistida por microondas a partir de Agaricus bisporus L., aplicando a técnica estatística de superfície e resposta combinada com a técnica de HPLC-UV

O aumento de consumo de cogumelos tem-se verificado em todo o mundo, não só pelo seu valor nutricional, sabor apurado e textura, mas também pelas suas propriedades medicinais. Existem vários estudos científicos que descrevem os benefícios do consumo de cogumelos, que advêm da sua riqueza em compostos bioativos, tais como micosteróis, em particular, ergosterol. Agaricus bisporus L. é o cogumelo mais consumido em todo o mundo, sendo a sua fração de esteróis constituída essencialmente por ergosterol (90%) [1], tornando a sua extração um tópico de elevado interesse já que esta molécula apresenta elevado valor comercial e inúmeras aplicações nas indústrias alimentar, farmacêutica e cosmética. Segundo a literatura, o teor de ergosterol pode variar entre 3 e 9 mg por g de cogumelo seco. Atualmente, os métodos tradicionais tais como a maceração e a extração em Soxhlet estão a ser substituídos por metodologias emergentes, nomeadamente a extração assistida por microondas, visando diminuir a quantidade de solvente utilizado e o tempo de extração e, naturalmente, aumentar o rendimento da mesma. No presente trabalho, utilizou-se A. bisporus como fonte de ergosterol, tendo-se otimizado as seguintes variáveis relevantes para a sua extração pela tecnologia de microondas (MAE): tempo (0-20 min), temperatura (60-210 ºC) e razão sólido-líquido (1-20 g/L). O solvente utilizado foi o etanol tendo-se aplicado a técnica estatística de superfície de resposta por forma a gerar modelos matemáticos que permitissem maximizar a resposta e otimizar as variáveis que afetam a extração de ergosterol. O conteúdo em ergosterol foi monitorizado por HPLC-UV. Os resultados demonstraram que a técnica MAE é promissora para a extração de ergosterol, tendo-se obtido, para as condições ótimas (20,4 min, 121,5ºC e 1,6 g/L), 569,4 mg ergosterol/100 g de massa seca, valor similar ao obtido com extração convencional por Soxhlet (671,5±0,5 mg/100 g de massa seca). Em síntese, a extração assistida por microondas demonstrou ser uma tecnologia eficiente para maximizar o rendimento de extração em ergosterol.

Avaliação dos cenários futuros na região nordeste do Brasil utilizando modelos climáticos globais: tendências de temperatura.

O Nordeste é a região brasileira mais vulnerável ao aquecimento global. Os modelos climáticos globais são a melhor ferramenta para projetar cenários prováveis de alterações climáticas para o futuro, apesar da incerteza envolvida. O objetivo deste trabalho foi realizada uma avaliação da tendência da temperatura média nos cenários futuros previstos pelos modelos climáticos globais do IPCC para região Nordeste do Brasil. Foi realizada uma análise estatística básica dos dados de comparação entre os modelos. Foi possível agrupar os modelos em 5 grupos, desde modelos estimando temperaturas médias comparativamente inferiores em todos os meses a outros com valores superiores em todos os meses.

Dinâmica fisiológica da variabilidade cardíaca: uma abordagem estatística na síncope vasovagal

Introdução: A perda transitória da consciência e tónus postural seguido de rápida recuperação é definida como síncope. Tem sido dada atenção a uma síncope de origem central com descida da pressão sistémica conhecida por síncope vasovagal (SVV). Objetivos: A análise da variabilidade da frequência cardíaca (HRV) é uma das principais estratégias para estudar a SVV através de protocolos padrão (por exemplo tilt test). O principal objetivo deste trabalho é compreender a importância relativa de diversas variáveis, tais como pressão arterial diastólica e sistólica, (dBP) e (sBP), volume sistólico (SV) e resistência periférica total (TPR) na HRV. Métodos: Foram usados modelos estatísticos mistos para modelar o comportamento das variáveis acima descritas na HRV. Analisaram-se mais de mil e quinhentas observações de quatro pacientes com SVV, previamente testados com análise espectral clássica para a fase basal (LF/HF=3.01) e fases de tilt (LF/HF=0.64), indicando uma predominância vagal no período tilt. Resultados: O modelo 1 revelou o papel importante da dBP e uma baixa influência de SV, na fase de tilt, relativos à HRV. No modelo 2 a TPR revelou uma baixa influência na HRV na fase de tilt entre os pacientes. Conclusões: Verificou-se que a HRV é influenciada por um conjunto de variáveis fisiológicas, cuja contribuição individual pode ser usada para compreender as flutuações cardíacas. O uso de modelos estatísticos salientou a importância de estudar o papel da dBP e SV na SVV.

Estatística aplicada à química: dez dúvidas comuns

Ten common doubts of chemistry students and professionals about their statistical applications are discussed. The use of the N-1 denominator instead of N is described for the standard deviation. The statistical meaning of the denominators of the root mean square error of calibration (RMSEC) and root mean square error of validation (RMSEV) are given for researchers using multivariate calibration methods. The reason why scientists and engineers use the average instead of the median is explained. Several problematic aspects about regression and correlation are treated. The popular use of triplicate experiments in teaching and research laboratories is seen to have its origin in statistical confidence intervals. Nonparametric statistics and bootstrapping methods round out the discussion.

Princípios fundamentais e modelos de transferência de energia inter e intramolecular

This work outlines the historic development of the concept and main theories of energy transfer, as well as the principal experiments carried out to confirm or refute the proposed theories. Energy transfer in coordination compounds is also discussed with a focus on rare earth systems.

Modelos de transferência de metal pesado na cana-de-açúcar adubada com composto de lixo urbano

The research approaches recycling of urban waste compost (UWC) as an alternative fertilizer for sugarcane crop and as a social and environmental solution to the solids residuals growth in urban centers. A mathematical model was used in order to know the metal dynamics as decision support tool, aiming to establish of criteria and procedures for UWC's safe use, limited by the amount of heavy metal. A compartmental model was developed from experimental data in controlled conditions and partially checked with field data. This model described the heavy metal transference in the system soil-root-aerial portion of sugarcane plants and concluded that nickel was metal to be concern, since it takes approximately three years to be attenuated in the soil, reaching the aerial portions of the plant at high concentrations. Regarding factors such as clay content, oxide level and soil pH, it was observed that for soil with higher buffering capacity, the transfer of the majority of the metals was slower. This model may become an important tool for the attainment of laws regarding the UWC use, aiming to reduce environment contamination the waste accumulation and production costs.

Modelos estatísticos indicadores de comportamentos associados a bem-estar térmico para matrizes pesadas

The study of female broiler breeders is of great importance for the country as poultry production is one of the largest export items, and Brazil is the second largest broiler meat exporter. Animal behavior is known as a response to the effect of several interaction factors among them the environment. In this way the internal housing environment is an element that gives hints regarding to the bird s thermal comfort. Female broiler breeder behavior, expresses in form of specific pattern the bird s health and welfare. This research had the objective of applying predictive statistical models through the use of simulation, presenting animal comfort scenarios facing distinct environmental conditions. The research was developed with data collected in a controlled environment using Hybro - PG® breeding submitted to distinct levels of temperature, three distinct types of standard ration and age. Descriptive and exploratory analysis were proceeded, and afterwards the modeling process using the Generalized Estimation Equation (GEE). The research allowed the development of the thermal comfort indicators by statistical model equations of predicting female broiler breeder behavior under distinct studied scenarios.

Estimativa de parâmetros biofísicos de plantios de café a partir de imagens orbitais de alta resolução espacial

Remote sensing data are each time more available and can be used to monitor the vegetal development of main agricultural crops, such as the Arabic coffee in Brazil, since that the relationship between spectral and agronomical data be well known. Therefore, this work had the main objective to assess the use of Quickbird satellite images to estimate biophysical parameters of coffee crop. Test area was composed by 25 coffee fields located between the cities of Ribeirão Corrente, Franca and Cristais Paulista (SP), Brazil, and the biophysical parameters used were row and between plants spacing, plant height, LAI, canopy diameter, percentage of vegetation cover, roughness and biomass. Spectral data were the reflectance of four bands of QUICKBIRD and values of four vegetations indexes (NDVI, GVI, SAVI and RVI) based on the same satellite. All these data were analyzed using linear and nonlinear regression methods to generate estimation models of biophysical parameters. The use of regression models based on nonlinear equations was more appropriate to estimate parameters such as the LAI and the percentage of biomass, important to indicate the productivity of coffee crop.