scholarly journals Análise bayesiana univariada e bivariada para a conversão alimentar de suínos da raça Piau

2014 ◽  
Vol 49 (10) ◽  
pp. 754-761 ◽  
Author(s):  
Robson Marcelo Rossi ◽  
Elias Nunes Martins ◽  
Paulo Sávio Lopes ◽  
Fabyano Fonseca e Silva
Keyword(s):  
Monte Carlo ◽  
Inferencia Bayesiana ◽  
Log Normal ◽  
Skew Normal

O objetivo deste trabalho foi apresentar modelagens alternativas, uni e bivariadas, para avaliação da conversão alimentar (CA) de suínos da raça Piau, com uso de inferência bayesiana. Os efeitos de sexo e genótipo sobre a CA dos animais foram avaliados por meio de procedimentos de simulação de Monte Carlo via cadeias de Markov (MCMC) e de integração aproximada aninhada de Laplace (INLA). O modelo univariado foi avaliado com diferentes distribuições para o erro - normal (gaussiana), t de Student, gama, log-normal e skew-normal -, enquanto, para o modelo bivariado, considerou-se o erro normal. A distribuição skew-normal foi o modelo mais parcimonioso para inferir sobre a resposta direta (univariada) da CA aos efeitos de sexo e genótipo, os quais não foram significativos. O modelo bivariado foi capaz de identificar diferenças significativas no ganho de peso e no consumo de ração em níveis de significância não detectados pelo modelo univariado. Além disso, ele também foi capaz de detectar diferenças entre sexos, quando agrupados por genótipos NN (machos, 2,73±0,04; fêmeas, 2,68±0,04) e Nn (machos, 2,70±0,07; fêmeas, 2,64±0,07), e revelou maior acurácia e precisão nas inferências nutricionais. Em ambas as abordagens, o método bayesiano mostra-se flexível e eficiente para a avaliação do desempenho nutricional dos animais.

scholarly journals Dynamical model for social distancing in the U.S. during the COVID-19 epidemic

2020 ◽  
Vol 8 (1) ◽  
pp. 141-149
Author(s):  
Shirish M. Chitanvis
Keyword(s):  
New York ◽  
Monte Carlo ◽  
Temporal Evolution ◽  
Social Experiment ◽  
Social Distancing ◽  
Back Testing ◽  
Moderate Growth ◽  
Log Normal ◽  
Very High ◽  
The U.S

AbstractBackground Social distancing has led to a “flattening of the curve” in many states across the U.S. This is part of a novel, massive, global social experiment which has served to mitigate the COVID-19 pandemic in the absence of a vaccine or effective anti-viral drugs. Hence it is important to be able to forecast hospitalizations reasonably accurately.Methods We propose on phenomenological grounds a random walk/generalized diffusion equation which incorporates the effect of social distancing to describe the temporal evolution of the probability of having a given number of hospitalizations. The probability density function is log-normal in the number of hospitalizations, which is useful in describing pandemics where the number of hospitalizations is very high.Findings We used this insight and data to make forecasts for states using Monte Carlo methods. Back testing validates our approach, which yields good results about a week into the future. States are beginning to reopen at the time of submission of this paper and our forecasts indicate possible precursors of increased hospitalizations. However, the trends we forecast for hospitalizations as well as infections thus far show moderate growth.Additionally we studied the reproducibility Ro in New York (Italian strain) and California (Wuhan strain). We find that even if there is a difference in the transmission of the two strains, social distancing has been able to control the progression of COVID 19.

Reliability Against Drifting Ice—An Adjunct to Monte Carlo Simulation

1991 ◽  
Vol 113 (3) ◽  
pp. 253-259
Author(s):  
A. B. Dunwoody
Keyword(s):  
Monte Carlo Simulation ◽  
Monte Carlo ◽  
Normal Family ◽  
Probability Distributions ◽  
Load Model ◽  
Ice Load ◽  
Ice Loads ◽  
Drifting Ice ◽  
Log Normal ◽  
Monte Carlo Simulation Program

A method is presented for the calculation of the reliability of a structure against drifting ice subject to restrictions on the form of the ice load model and on the form of the probability distributions of the ice feature characteristics. The ice load model must have the form that the ice load is proportional to the product of the characteristics of the impacting ice feature raised to individual powers. Results from a Monte Carlo simulation program are presented to demonstrate that the ice loads for a number of useful ice interaction scenarios can be modeled by an equation of this form. The probability distributions of the ice feature characteristics must be from the log-normal family. A realistic example using publicly available ice data and ice load model is presented.

On the quasi-Monte Carlo method with Halton points for elliptic PDEs with log-normal diffusion

2016 ◽  
Vol 86 (304) ◽  
pp. 771-797 ◽  
Author(s):  
Helmut Harbrecht ◽  
Michael Peters ◽  
Markus Siebenmorgen
Keyword(s):  
Monte Carlo ◽  
Monte Carlo Method ◽  
Elliptic Pdes ◽  
Quasi Monte Carlo ◽  
Normal Diffusion ◽  
Log Normal

Monte-Carlo Modeling of Recrystallization Kinetics of Cold-Rolled Titanium

2010 ◽  
Vol 654-656 ◽  
pp. 1486-1491 ◽  
Author(s):  
Y.B. Chun ◽  
S. Lee Semiatin ◽  
Sun Keun Hwang
Keyword(s):  
Monte Carlo ◽  
Heterogeneous Nucleation ◽  
Negative Deviation ◽  
Stored Energy ◽  
High Deformation ◽  
Recrystallization Kinetics ◽  
Cold Rolled ◽  
Log Normal ◽  
Kinetics Of ◽  
Log Normal Distribution

The recrystallization behavior of cold-rolled, commercial-purity titanium was studied experimentally and with Monte-Carlo (MC) modeling. Utilization of EBSD-OIM as input for MC modeling resulted in realistic predictions of recrystallization kinetics, microstructure and texture, which were in good agreement with experimental results. MC modeling of recrystallization kinetics predicted that the non-uniform stored energy distribution, heterogeneous nucleation of recrystallization and recovery in combination leads to a negative deviation from linear JMAK kinetics. It was found that concurrent recovery that takes place during recrystallization is an important process that controls both the overall recrystallization kinetics and the deviation of linear JMAK kinetics. On the other hand, the non-uniformly distributed stored energy itself has little effect on the negative deviation from JMAK kinetics but intensifies the deviation when heterogeneous nucleation is combined. Modeling results also revealed that heterogeneous nucleation of recrystallized grains and their early impingement in local areas of high deformation are essential for producing a log-normal distribution of grain size and a typical recrystallization texture of rolled titanium.

A Bayesian Monte Carlo Markov Chain Method for Loss Models and Risk Measure Assessments

2009 ◽  
Vol 12 (03) ◽  
pp. 529-543
Author(s):  
Ling Hu ◽  
Yating Yang
Keyword(s):  
Monte Carlo ◽  
Markov Chain ◽  
Normal Distribution ◽  
Risk Measure ◽  
Markov Chain Method ◽  
Flood Loss ◽  
Bayesian Monte Carlo ◽  
Loss Models ◽  
Log Normal ◽  
Log Normal Distribution

Natural disasters are also known as catastrophes with low frequency but high damages. Typhoons and floods are the major catastrophes which lead to gargantuan losses in Asia. Once a disaster occurs, a broad region will be affected and this will result in huge social loss. If issuers or governments use the wrong loss models or risk measure indexes to price the related insurance products, they will get an inaccurate price and thus be insolvent to the claims. Previous researches often use a Log-Normal distribution to model a catastrophic loss. This is not appropriate since the characteristics of a loss distribution have some empirical facts, including the positive skewness and the heavy-tailed properties. Recently, some studies (McNeil and Frey, 2000; Rootzen and Tajvidi, 2000; Thuring et al., 2008) also point out that using Log-Normal distribution to model a characteristic loss is not suitable. Therefore, we build a typhoon and flood loss model with higher order moments and estimate the parameters through a Bayesian Monte Carlo Markov Chain method. According to the Kolmogorov-Smirnov test, we find that the Pareto distribution is more adaptive for modeling the loss of typhoon and flood. Further, we evaluate different kinds of risk measure indexes through simulating and numerical analysis. It gives the beacon to issuers or governments when they want to issue the insurance products about typhoon and flood loss.

Estimation of log-normal quantiles: Monte Carlo results and first-order approximations

1984 ◽  
Vol 71 (1-2) ◽  
pp. 1-30 ◽  
Author(s):  
Kiyoshi Hoshi ◽  
Jery R Stedinger ◽  
Stephen J Burges
Keyword(s):  
Monte Carlo ◽  
First Order ◽  
Log Normal

scholarly journals Dynamical model for social distancing in the U.S. during the COVID-19 epidemic

2020 ◽  
Author(s):  
Shirish M Chitanvis
Keyword(s):  
New York ◽  
Monte Carlo ◽  
Probability Density Function ◽  
Temporal Evolution ◽  
Social Experiment ◽  
Social Distancing ◽  
Back Testing ◽  
Log Normal ◽  
Very High ◽  
The U.S

Background Social distancing has led to a flattening of the curve in many states across the U.S. This is part of a novel, massive, global social experiment which has served to mitigate the pandemic in the absence of a vaccine or effective anti-viral drugs. Hence it is important to be able to forecast hospitalizations reasonably accurately. Methods We propose on phenomenological grounds a generalized diffusion equation which in- corporates the effect of social distancing to forecast the temporal evolution of the probability of having a given number of hospitalizations. The probability density function is log-normal in the number of hospitalizations, which is useful in describing pandemics where the number of hospital- izations is very high. Findings We used this insight and data to make forecasts for states using Monte Carlo methods. Back testing validates our approach, which yields good results about a week into the future. States are beginning to reopen at the time of publication and our forecasts indicate possible precursors of increased hospitalizations. Additionally we studied the reproducibility Ro in New York (Italian strain) and California (Wuhan strain). We find that even if there is a difference in the transmission of the two strains, social distancing has been able to control the progression of COVID 19. Funding None.

Probabilistic Carbonation Simulations in Concrete Based on Marble Powder

2020 ◽  
Vol 1013 ◽  
pp. 114-119
Author(s):  
Azhar Badaoui
Keyword(s):  
Monte Carlo ◽  
Probability Distribution ◽  
Random Variable ◽  
Carbonation Depth ◽  
Concrete Carbonation ◽  
Normal Probability ◽  
Powder Diameter ◽  
Marble Powder ◽  
Normal Probability Distribution ◽  
Log Normal

The aim of this paper is the evaluation of concrete carbonation depth from a probabilistic analysis, focusing specifically on the study of the marble powder diameters randomness effect on the reinforced concrete carbonation. Monte Carlo simulations are realized under the assumption that the marble powder diameter (Dmp) is random variable with a log-normal probability distribution.

scholarly journals Conjugate Bayes for probit regression via unified skew-normal distributions

Biometrika ◽  
2019 ◽  
Vol 106 (4) ◽  
pp. 765-779 ◽  
Author(s):  
Daniele Durante
Keyword(s):  
Monte Carlo ◽  
Markov Chain ◽  
Markov Chain Monte Carlo ◽  
Computational Methods ◽  
Graphical Models ◽  
Building Blocks ◽  
Probit Regression ◽  
Conjugate Priors ◽  
Dichotomous Data ◽  
Skew Normal

Summary Regression models for dichotomous data are ubiquitous in statistics. Besides being useful for inference on binary responses, these methods serve as building blocks in more complex formulations, such as density regression, nonparametric classification and graphical models. Within the Bayesian framework, inference proceeds by updating the priors for the coefficients, typically taken to be Gaussians, with the likelihood induced by probit or logit regressions for the responses. In this updating, the apparent absence of a tractable posterior has motivated a variety of computational methods, including Markov chain Monte Carlo routines and algorithms that approximate the posterior. Despite being implemented routinely, Markov chain Monte Carlo strategies have mixing or time-inefficiency issues in large-$p$ and small-$n$ studies, whereas approximate routines fail to capture the skewness typically observed in the posterior. In this article it is proved that the posterior distribution for the probit coefficients has a unified skew-normal kernel under Gaussian priors. This result allows efficient Bayesian inference for a wide class of applications, especially in large-$p$ and small-to-moderate-$n$ settings where state-of-the-art computational methods face notable challenges. These advances are illustrated in a genetic study, and further motivate the development of a wider class of conjugate priors for probit models, along with methods for obtaining independent and identically distributed samples from the unified skew-normal posterior.

Sign in / Sign up

Export Citation Format

Share Document