Otro
Inferência bayesiana na predição de valores genéticos do peso aos 365 dias de bovinos de corte
Registro en:
Archivos de Zootecnia, v. 58, n. 222, p. 265-275, 2009.
0004-0592
1885-4494
10.4321/S0004-05922009000200011
S0004-05922009000200011
S0004-05922009000200011.pdf
2-s2.0-67549147013
Autor
Madureira, A. P.
Oliveira, H. N.
Rosa, G. J. M.
Bezerra, L. F.
Marques, L. F. A.
Resumen
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.