Robust linear mixed models with normal/independent distributions and Bayesian MCMC implementation

Linear mixed effects models have been widely used in analysis of data where responses are clustered around some random effects, so it is not reasonable to assume independence between observations in the same cluster. In most biological applications, it is assumed that the distributions of the random effects and of the residuals are Gaussian. This makes inferences vulnerable to the presence of outliers. Here, linear mixed effects models with normal/independent residual distributions for robust inferences are described. Specific distributions examined include univariate and multivariate versions of the Student-t, the slash and the contaminated normal. A Bayesian framework is adopted and Markov chain Monte Carlo is used to carry out the posterior analysis. The procedures are illustrated using birth weight data on rats in a texicological experiment. Results from the Gaussian and robust models are contrasted, and it is shown how the implementation can be used for outlier detection. The thick-tailed distributions provide an appealing robust alternative to the Gaussian process in linear mixed models, and they are easily implemented using data augmentation and MCMC techniques.

Correlações entre deslocamento e conformação em eqüinos Mangalarga

The aim of this study was estimate genetic, environmental and phenotypic correlations between movement and conformation traits in Mangalarga horses, in Brazil. The data were provided by Brazilian Association of Mangalarga Horses Breeders, comprised 9865 observations for movement and conformation traits. The data were organized by SAS, and the (co)variance components were estimated by the program MTGSAM. The heritabilities estimates varied from 0.22 (shoulder) to 0.29 (limbs), and the genetic correlations ranged from 0.51 (movement and neck) to 0.31 (movement and limbs).

Inferência bayesiana na predição de valores genéticos do peso aos 365 dias de bovinos de corte

Data from purebred Simmental, Nellore and Canchim cattle breeds obtained from the respective Brazilian Associations of Breeders were used to estimate variance components and to predict genetic values for 365 days weight. The results obtained by Bayesian inference were compared to those from Restricted Maximum Likelihood (REML) and Best Linear Unbiased Prediction (BLUP), which are the most commonly used methods of estimation and prediction in animal breeding. The two methods presented similar point estimates but the study of the marginal posterior distributions in the Bayesian approach yields more detailed information about the parameters and other unknowns in the model.

Genetic variability for temperament indicators of Nellore cattle

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Multiple-trait random regression models for the estimation of genetic parameters for milk, fat, and protein yield in buffaloes

In this study, genetic parameters for test-day milk, fat, and protein yield were estimated for the first lactation. The data analyzed consisted of 1,433 first lactations of Murrah buffaloes, daughters of 113 sires from 12 herds in the state of São Paulo, Brazil, with calvings from 1985 to 2007. Ten-month classes of lactation days were considered for the test-day yields. The (co)variance components for the 3 traits were estimated using the regression analyses by Bayesian inference applying an animal model by Gibbs sampling. The contemporary groups were defined as herd-year-month of the test day. In the model, the random effects were additive genetic, permanent environment, and residual. The fixed effects were contemporary group and number of milkings (1 or 2), the linear and quadratic effects of the covariable age of the buffalo at calving, as well as the mean lactation curve of the population, which was modeled by orthogonal Legendre polynomials of fourth order. The random effects for the traits studied were modeled by Legendre polynomials of third and fourth order for additive genetic and permanent environment, respectively, the residual variances were modeled considering 4 residual classes. The heritability estimates for the traits were moderate (from 0.21-0.38), with higher estimates in the intermediate lactation phase. The genetic correlation estimates within and among the traits varied from 0.05 to 0.99. The results indicate that the selection for any trait test day will result in an indirect genetic gain for milk, fat, and protein yield in all periods of the lactation curve. The accuracy associated with estimated breeding values obtained using multi-trait random regression was slightly higher (around 8%) compared with single-trait random regression. This difference may be because to the greater amount of information available per animal. © 2013 American Dairy Science Association.

Genetic parameters for scrotal circumference, breeding soundness examination and sperm defects in young Nellore bulls

A total of 51,161 records of scrotal circumference measurements at 18 mo of age (SCI 8) and 17,648 records of sperm defects and breeding soundness of Nellore bulls (mean age of 22.5 mo), raised under extensive conditions, were analyzed to estimate coefficients of heritability and genetic correlations of morphological semen traits by Bayesian inference. The observed semen traits were classified as minor (MID). major (MAD), and total sperm defects (TD). The animals were classified according to breeding soundness as satisfactory and unsatisfactory potential breeders. The (co)variance components and breeding values were estimated by Gibbs sampling using the GIBBS2F90 program under an animal model that included contemporary group as fixed effect, age of animal as linear covariate, and direct additive genetic effects as random effects. Heritabilities of 0.40 ± 0.02, 0.16 ± 0.02, 0.04 ± 0.01, 0.15 ± 0.01, and 0.10 ± 0.01 were obtained for SCI8, MID, MAD, TD, and breeding soundness, respectively. The SC18 showed a positive and moderate correlation with breeding soundness (0.56 ± 0.04) and a negative and low correlation with MID (-0.23 ± 0.03), MAD (-0.16 ± 0.02), and TD (-0.24 ± 0.02). In conclusion, scrotal circumference showed the best response to selection among the traits studied and was favorably correlated with breeding soundness and sperm morphology in young Nellore bulls. © 2013 American Society of Animal Science. All rights reserved.

Parâmetros genéticos para rentabilidade monetária em cavalos de corrida da raça Quarto de Milha

Pós-graduação em Genética e Melhoramento Animal - FCAV

Análise bayesiana do modelo fatorial dinâmico para um vetor de séries temporais utilizando a distribuição t multivariada

The multivariate t models are symmetric and with heavier tail than the normal distribution, important feature in financial data. In this theses is presented the Bayesian estimation of a dynamic factor model, where the factors follow a multivariate autoregressive model, using multivariate t distribution. Since the multivariate t distribution is complex, it was represented in this work as a mix between a multivariate normal distribution and a square root of a chi-square distribution. This method allowed to define the posteriors. The inference on the parameters was made taking a sample of the posterior distribution, through the Gibbs Sampler. The convergence was verified through graphical analysis and the convergence tests Geweke (1992) and Raftery & Lewis (1992a). The method was applied in simulated data and in the indexes of the major stock exchanges in the world.

Métodos para avaliação do temperamento de bovinos: estimação de parâmetros genéticos e relações com o desempenho

Pós-graduação em Genética e Melhoramento Animal - FCAV

Análise Bayesiana da área de olho do lombo e da espessura de gordura obtidas por ultrassom e suas associações com outras características de importância econômica na raça Nelore

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Análise da curva de crescimento de bovinos da raça Nelore utilizando funções não-lineares em análises Bayesianas: Selma Forni. -

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Modelos de antedependência para avaliação genética de características longitudinais

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Estudo da interação genótipo x ambiente sobre a produção de leite em rebanhos da raça Parodo-Suiço no Brasil, utilizando inferência Bayesiana

Verifica a presença de heterogeneidade de variâncias sobre a produção de leite na primeira lactação de fêmeas da raça Pardo-Suíço e, seu impacto sobre a avaliação genética dos reprodutores, utilizando a inferência Bayesiana por meio de amostrador de Gibbs, foram utilizados 2981 registros referentes às produções de leite e idade da vaca ao parto, em primeiras lactações de vacas da raça Pardo-Suíço, distribuídos em 62 rebanhos. Os registros foram provenientes do serviço de controle leiteiro da Associação Brasileira de Criadores de Gado Pardo Suíço, com os partos ocorridos entre os anos de 1980 a 2002. Foram estabelecidas duas classes de desvio-padrão fenotípico para produção de leite. Posteriormente, os dados foram analisados desconsiderando e considerando as classes de desvio-padrão. As médias observadas e desvio-padrão para produção de leite nas classes de alto e baixo desviopadrão e em análise geral foram iguais a 5802,02 ± 1929,96, 4844,37 ± 1592,99, 5373,47 ± 1849,13, respectivamente. As médias posteriores para os componentes de variâncias foram maiores na classe de alto desvio-padrão. A herdabilidade obtida na classe de alto desviopadrão foi próxima do valor observado na análise geral e inferior ao valor encontrado na classe de baixo desvio-padrão fenotípico. A correlação genética para a produção de leite entre as classes de desvio-padrão foi igual a 0,48. As correlações de Pearson e Spearman entre os valores genéticos para a produção de leite obtidos na análise geral, com os valores obtidos em cada classe de desvio-padrão foram todas maiores que 0,80, quando se considerou todos os reprodutores. Porém, refinando a amostra de reprodutores verifica-se que, as correlações diminuem em magnitude. Existindo uma maior variabilidade nos rebanhos presentes na classe de alto desvio-padrão e, o impacto dessa heterogeneidade de variância sobre a avaliação genética de reprodutores, é pequeno, pois a fonte principal dessa heterogeneidade é decorrente de fatores genéticos confirmando a presença de heterogeneidade de variâncias.

Estudo genético quantitativo das características andrológicas de touros jovens da raça Nelore

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Genetic Parameters for Productive and Reproductive Traits for Milk Buffalo in Brazil

Knowing the genetic parameters of productive and reproductive traits in milking buffaloes is essential for planning and implementing of a program genetic selection. In Brazil, this information is still scarce. The objective of this study was to verify the existence of genetic variability in milk yield of buffaloes and their constituents, and reproductive traits for the possibility of application of the selection. A total of 9,318 lactations records from 3,061 cows were used to estimate heritabilities for milk yield (MY), fat percentage (%F), protein percentage (%P), length of lactation (LL), age of first calving (AFC) and calving interval (CI) and the genetic correlations among traits MY, %F and %P. The (co) variance components were estimated using multiple-trait analysis by Bayesian inference method, applying an animal model, through Gibbs sampling. The model included the fixed effects of contemporary groups (herd-year and calving season), number of milking (2 levels), and age of cow at calving as (co) variable (quadratic and linear effect). The additive genetic, permanent environmental, and residual effects were included as random effects in the model. Estimated heritability values for MY, % F, % P, LL, AFC and CI were 0.24, 0.34, 0.40, 0.09, 0.16 and 0.05, respectively. The genetic correlation estimates among MY and % F, MY and % P and % F and % P were -0.29, -0.18 and 0.25, respectively. The production of milk and its constituents showed enough genetic variation to respond to a selection program. Negative estimates of genetic correlations between milk production and its components suggest that selection entails a reduction in the other.