The Gaussian distribution is often adopted for statistical modeling of genetic evaluations of the Simmental breed in Brazil. For some traits, however, the Gaussian process does not present a good approximation of the sampling model because of heterogeneity of the data and/or the presence of outliers. Some thick-tailed distributions have been suggested in the literature as alternatives to the normal distribution, such as the Student-t process (Strandén and Gianola, 1999; Rosa, 1999). Here, a mixture of Gaussian distributions is discussed within the mixedmodel and animal-breeding context. A Bayesian framework is adopted and Markov chain Monte Carlo is used to carry out the posterior analysis. The methodology is applied to variance component estimation and genetic evaluation of yearling weight in Simmental breed. 

Henrique N Oliveira, G. B Santos, L. FA Marques, G. JM Rosa

Proceedings of the World Congress on Genetics Applied to Livestock Production, Volume 2002. Session 16, , 16.11, 2002
Download Full PDF BibTEX Citation Endnote Citation Search the Proceedings

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.