VARIANCE COMPONENT ESTIMATION IN ANIMAL BREEDING - A REVIEW

The goal of animal breeding is to improve performance traits of animal populations through selection. The selection criterion is usually bas ed on best linear unbiased prediction (BLUP) of additive genetic effec ts. BLUP requires knowledge about variance components that have to be estimated in practice. Due to its desirable properties restricted maxi mum likelihood (REML) has become the method of choice for the estimati on of variance components of mixed linear models in animal breeding. I mpressive progress has been made in the development of efficient compu ting algorithms that allow REML to be used for general mixed linear mo dels of large data sets. Various flexible computer programs have becom e available. Due to the adoption of Markov chain Monte Carlo procedure s Bayesian estimation has recently become feasible and is increasingly used in animal breeding applications. The availability of powerful co mputers and advances in the efficiency of computing algorithms allow t he consideration in the of increasingly complex models. Therefore, the development and application of appropriate statistical procedures for mobel comparison is becoming more important.