Bayesian inference for two-parameter gamma distribution assuming different noninformative priors

In this paper distinct prior distributions are derived in a Bayesian inference of the two-parameters Gamma distribution. Noniformative priors, such as Jeffreys, reference, MDIP, Tibshirani and an innovative prior based on the copula approach are investigated. We show that the maximal data information prior provides in an improper posterior density and that the different choices of the parameter of interest lead to different reference priors in this case. Based on the simulated data sets, the Bayesian estimates and credible intervals for the unknown parameters are computed and the performance of the prior distributions are evaluated. The Bayesian analysis is conducted using the Markov Chain Monte Carlo (MCMC) methods to generate samples from the posterior distributions under the above priors.

Theorem for series in three-parameter mittag-leffler function

The new result presented here is a theorem involving series in the three-parameter Mittag-Le er function. As a by-product, we recover some known results and discuss corollaries. As an application, we obtain the solution of a fractional di erential equation associated with a RLC electrical circuit in a closed form, in terms of the two-parameter Mittag-Le er function.

On the Generalized Mittag-Leffler Function and its Application in a Fractional Telegraph Equation

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

On anomalous diffusion and the fractional generalized Langevin equation for a harmonic oscillator

The fractional generalized Langevin equation (FGLE) is proposed to discuss the anomalous diffusive behavior of a harmonic oscillator driven by a two-parameter Mittag-Leffler noise. The solution of this FGLE is discussed by means of the Laplace transform methodology and the kernels are presented in terms of the three-parameter Mittag-Leffler functions. Recent results associated with a generalized Langevin equation are recovered.

Describing fatigue crack growth and load ratio effects in Al 2524 T3 alloy with an enhanced exponential model

The fatigue crack behavior in metals and alloys under constant amplitude test conditions is usually described by relationships between the crack growth rate da/dN and the stress intensity factor range Delta K. In the present work, an enhanced two-parameter exponential equation of fatigue crack growth was introduced in order to describe sub-critical crack propagation behavior of Al 2524-T3 alloy, commonly used in aircraft engineering applications. It was demonstrated that besides adequately correlating the load ratio effects, the exponential model also accounts for the slight deviations from linearity shown by the experimental curves. A comparison with Elber, Kujawski and "Unified Approach" models allowed for verifying the better performance, when confronted to the other tested models, presented by the exponential model. (C) 2012 Elsevier Ltd. All rights reserved.

Deep barcode divergence in Brazilian freshwater fishes: the case of the Sao Francisco River basin

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

DNA barcoding reveals hidden diversity in the Neotropical freshwater fish Piabina argentea (Characiformes: Characidae) from the Upper Parana Basin of Brazil

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

DNA barcodes discriminate freshwater fishes from the Paraiba do Sul River Basin, São Paulo, Brazil

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Máxima fase estável de lactato sanguíneo e potência crítica em ciclistas bem treinados

O principal objetivo deste estudo foi comparar a intensidade correspondente à máxima fase estável de lactato (MLSS) e a potência crítica (PC) durante o ciclismo em indivíduos bem treinados. Seis ciclistas do sexo masculino (25,5 ± 4,4 anos, 68,8 ± 3,0kg, 173,0 ± 4,0cm) realizaram em diferentes dias os seguintes testes: exercício incremental até a exaustão para a determinação do pico de consumo de oxigênio (VO2pico) e sua respectiva intensidade (IVO2pico); cinco a sete testes de carga constante para a determinação da MLSS e da PC; e um exercício até a exaustão na PC. A MLSS foi considerada com a maior intensidade de exercício onde a concentração de lactato não aumentou mais do que 1mM entre o 10º e o 30º min de exercício. Os valores individuais de potência (95, 100 e 110% IVO2pico) e seu respectivo tempo máximo de exercício (Tlim) foram ajustados a partir do modelo hiperbólico de dois parâmetros para a determinação da PC. Embora altamente correlacionadas (r = 0,99; p = 0,0001), a PC (313,5 ± 32,3W) foi significantemente maior do que a MLLS (287,0 ± 37,8W) (p = 0,0002). A diferença percentual da PC em relação à MLSS foi de 9,5 ± 3,1%. No exercício realizado na PC, embora tenha existido componente lento do VO2 (CL = 400,8 ± 267,0 ml.min-1), o VO2pico não foi alcançado (91,1 ± 3,3 %). Com base nesses resultados pode-se concluir que a PC e a MLSS identificam diferentes intensidades de exercício, mesmo em atletas com elevada aptidão aeróbia. Entretanto, o percentual da diferença entre a MLLS e PC (9%) indica que relação entre esses dois índices pode depender da aptidão aeróbia. Durante o exercício realizado até a exaustão na PC, o CL que é desenvolvido não permite que o VO2pico seja alcançado.

A thermoporometry and small-angle x-ray scattering study of wet silica sonogels as the pore volume fraction is varied

Silica sonogels with different porosities were prepared by acid sono-hydrolysis of tetraethoxysilane. Wet sonogels were studied using small-angle x-ray scattering (SAXS) and differential scanning calorimetry (DSC). The DSC shows a broad thermal peak below the normal water melting point associated with the melting of confined ice nanocrystals, or nanoporosity. The nanopore size distribution was determined from the Gibbs-Thomson equation. As the porosity is increased, a second sharp DSC thermal peak with onset temperature at the water melting point is apparent, which was associated with the melting of ice macrocrystals, or macroporosity. The DSC result could be causing misinterpretation of the macroporosity because water may not be exactly confined in very feeble silica network regions in sonogels with high porosity. The structure of the wet gels can be described fairly well as mutually self-similar mass fractal structures with characteristic length. increasing from similar to 1.8 to similar to 5.4 nm and mass fractal dimension D diminishing discretely from similar to 2.6 to similar to 2.3 as the porosity increases in the range studied. More specifically, such a structure could be described using a two-parameter correlation function gamma(r) similar to r(D-3) exp(-r/xi), which is limited at larger scale by the cut-off distance xi but without a well-defined small scale cut-off distance, at least up to the maximum angular domain probed using SAXS in the present study.

Correlation between solvation of peptide-resins and solvent properties

The solvation properties of model resin and peptide-resins measured in ca. 30 solvent systems correlated better with the sum of solvent electron acceptor (AN) and electron donor (DN) numbers, in 1:1 proportion, than with other solvent polarity parameters. The high sensitivity of the (AN+DN) term to detect differentiated solvation behaviors of peptide-resins, taken as model of heterogeneous and complex solutes, seems to be in agreement with the previously proposed two-parameter model, where the sum of the Lewis acidity and Lewis basicity characters of solvent are proposed for scaling solvent effect. Besides these physicochemical aspects regarding solute-solvent interactions, important implications of this study for the solid phase peptide synthesis were also observed. Each class of peptide-resin displayed a specific salvation profile that was dependent on the amount and the nature of the resin-bound peptide sequence. Plots of resin swelling versus solvent (AN+DN) values allowed the visualization of a maximum salvation region characteristic for each class of resin. This strategy facilitates the selection of solvent systems for optimal solvation conditions of peptide chains in every step of the entire synthesis cycle. Moreover, only the AN and DN concepts allow the understanding of rules for solvation/shrinking of peptide-resins when in homogeneous or in heterogeneous mixed solvents.

Heat transfer in fixed bed: a model non-linearity approach

Studies have been carried out on the heat transfer in a packed bed of glass beads percolated by air at moderate flow rates. Rigorous statistic analysis of the experimental data was carried out and the traditional two parameter model was used to represent them. The parameters estimated were the effective radial thermal conductivity, k, and the wall coefficient, h, through the least squares method. The results were evaluated as to the boundary bed inlet temperature, T-o, number of terms of the solution series and number of experimental points used in the estimate. Results indicated that a small difference in T-o was sufficient to promote great modifications in the estimated parameters and in the statistical properties of the model. The use of replicas at points of high parametric information of the model improved the results, although analysis of the residuals has resulted in the rejection of this alternative. In order to evaluate cion-linearity of the model, Bates and Watts (1988) curvature measurements and the Box (1971) biases of the coefficients were calculated. The intrinsic curvatures of the model (IN) tend to be concentrated at low bed heights and those due to parameter effects (PE) are spread all over the bed. The Box biases indicated both parameters as responsible for the curvatures PE, h being somewhat more problematic. (C) 2000 Elsevier B.V. Ltd. All rights reserved.

Non-periodic bifurcations of one-dimensional maps

We prove that a 'positive probability' subset of the boundary of '{uniformly expanding circle transformations}' consists of Kupka-Smale maps. More precisely, we construct an open class of two-parameter families of circle maps (f(alpha,theta))(alpha,theta) such that, for a positive Lebesgue measure subset of values of alpha, the family (f(alpha,theta))(theta) crosses the boundary of the uniformly expanding domain at a map for which all periodic points are hyperbolic (expanding) and no critical point is pre-periodic. Furthermore, these maps admit an absolutely continuous invariant measure. We also provide information about the geometry of the boundary of the set of hyperbolic maps.

Tin(II)-EDTA complex: kinetic of thermal decomposition by non-isothermal procedures

Tin on the oxide form, alone or doped with others metals, has been extensively used as gas sensor, thus, this work reports on the preparation and kinetic parameters regarding the thermal decomposition of Sn(II)-ethylenediaminetetraacetate as precursor to SnO2. Thus, the acquaintance with the kinetic model regarding the thermal decomposition of the tin complex may leave the door open to foresee, whether it is possible to get thin film of SnO2 using Sn(II)-EDTA as precursor besides the influence of dopants added.The Sn(II)-EDTA soluble complex was prepared in aqueous medium by adding of tin(II) chloride acid solution to equimolar amount of ammonium salt from EDTA under N-2 atmosphere and temperature of 50degreesC arising the pH similar to 4. The compound was crystallized in ethanol at low-temperature and filtered to eliminate the chloride ions, obtaining the heptacoordinated chelate with the composition H2SnH2O(CH2N(CH2COO)(2))(2).0.5H(2)O.Results from TG, DTG and DSC curves under inert and oxidizing atmospheres indicate the presence of water coordinated to the metal and that the ethylenediamine fraction is thermally more stable than carboxylate groups. The final residue from thermal decomposition was the SnO2 characterized by X-ray as a tetragonal rutile phase.Applying the isoconversional Wall-Flynn-Ozawa method on the DSC curves, average activation energy: E-a = 183.7 +/- 12.7 and 218.9 +/- 2.1 kJ mol(-1), and pre-exponential factor: log A = 18.85 +/- 0.27 and 19.10 +/- 0.27 min(-1), at 95% confidence level, could be obtained, regarding the loss of coordinated water and thermal decomposition of the carboxylate groups, respectively. The E-a and logA also could be obtained applying isoconventional Wall-Flynn method on the TG curves.From E-a and log A values, Dollimore and Malek procedures could be applied suggesting R3 (contracting volume) and SB (two-parameter model) as the kinetic model to the loss of coordinated water (177-244degreesC) and thermal decomposition of the carboxylate groups (283-315degreesC), respectively. Simulated and experimental normalized DTG and DSC curves besides analysis of residuals check these kinetic models. (C) 2003 Elsevier B.V. All rights reserved.

The Poisson-exponential distribution: a Bayesian approach

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)