Page 255 - Linear Models for the Prediction of Animal Breeding Values 3rd Edition

with V estimated as Eqn 13.25 and l is an arbitrary weight such that S l = 1.
iklj ikl ikl ikl
1
For the example data, l can be set to be equal to , as there are eight region–season–
8 1
sex of calf subclasses. The probabilities obtained using Eqn 13.26 with l = were
8
0.167, 0.188, 0.169, 0.189, 0.183 and 0.187 for sires 1, 2, 3, 4, 5 and 6,
respectively.
The analysis of a binary trait with a quantitative trait has been discussed and
illustrated in this section. However, if the category trait has several thresholds, then
the method discussed in Section 13.2 would be used for the analysis of the categorical
trait.

Analysis of Ordered Categorical Traits 239