Comparison between linear mixed model and threshold model in the estimation of variance components in age at first calving and milk production in buffaloes

Abstract

The genetic evaluation of Murrah buffaloes can be optimized by associating milk production, genetic value of sires, and age at first calving. Therefore, the aim of this study was to compare the Linear Mixed Model with the Threshold Model and their genetic association with milk production and the genetic evaluation of sires in the estimation of variance components of age at first calving in Murrah buffalo. The dataset comprised information on total milk production and age at first calving of Murrah buffaloes. The mixed linear animal model, designated as Model 1, was employed to estimate variance components. In a subsequent analysis, designated as Model 2, the age at first calving was examined in conjunction with the milk production. The variance components were obtained by Bayesian inference, using the Gibbs sampler to obtain posterior means. The t-test was then applied in order to compare the means of two samples. The additive genetic correlations between milk production and age at first calving were low in both models, with values equal to 0.11 and 0.17 for Models 1 and 2, respectively. The descriptive analysis of the predicted breeding values revealed that, irrespective of the model, the values for milk production exhibited minimal variation. In a separate analysis, Model 2 exhibited a reduced amplitude for age at first calving and enhanced prediction accuracy, particularly for sires with negative breeding values for this trait. Consequently, the Threshold Model strategy for analyzing age at first calving variance components is more efficient than a Linear Mixed Model. It provides more accurate genetic value estimates for sires without affecting milk production predictions.

Keywords: Bayesian inference; Geweke test; Gibbs sampler; Markov chains via Monte Carlo; Murrah breed.