Aplicação do modelo de limiar utilizando a Inferência Bayesiana no melhoramento animal

Abstract

The application of modern methods using the animal model is essential for the efficient conduct of any breeding program. The procedures to characteristics in which continuous variation is assumed are not suitable for those with non-continuous variation. In threshold model assumes that the answering process is associated with an underlying continuous variable which has continuous normal distribution. The probabilistic representation of all knowledge uncertain is the essence of Bayesian inference, such knowledge is related to future observable quantities or unknown parameters. The priori and posteriori concepts are always relative to the observation at the time considered. Thus, we aimed at with this revision presenting and discussing some trends and applications of threshold model with a focus on Bayesian inference, applied to animal breeding.

Threshold models for the determination of genetic variability among reproductive traits in Nellore cattle

“…Categorical traits that can be distinguished into phenotypic classes are called threshold traits. The procedures for defining the phenotypic expression of these traits, and analyzing the underlying genetic data vary according to the number of classes per variable (Santos et al, 2012;Malhado et al, 2013), and according to the complexity of the interactions between the environment, animal genetics, physiology, and animal management. Not surprisingly, the application and definition of these traits as selection criteria remain poorly explored.…”