Adjustment for heterogeneous genetic and non-genetic (co) variance structures in test-day models using a transformation on random regression effect regressors

A method of accounting for differences in variation in components of test-day milk production records was developed. This method could improve accuracy of genetic evaluations. A random regression model is used to analyze data, and then a transformation is applied to the random regression coefficients. When evaluations with and without this transformation were compared, rankings of animals were similar but some re-rankings occurred. A correlation analysis showed a reduction in effect of production level on variation on regression coefficients, which indicated the success of the transformation.