Prediction Theory 1 Introduction 2 General Linear Mixed Model
Prediction Theory 1 Introduction 2 General Linear Mixed Model
Prediction Theory 1 Introduction 2 General Linear Mixed Model
Create successful ePaper yourself
Turn your PDF publications into a flip-book with our unique Google optimized e-Paper software.
17.1 Operational <strong>Model</strong>s<br />
Let<br />
y ijk = µ + C i + S j + e ijk ,<br />
where y ijk are the observations on the trait of interest of individual progeny, assumed to be one<br />
record per progeny only, µ is an overall mean, C i is a random contemporary group effect, S j is<br />
a random sire effect, and e ijk is a random residual error term associated with each observation.<br />
E(y ijk ) = µ,<br />
V ar(e ijk ) = σe<br />
2<br />
V ar(C i ) = σc 2 = σe/6.0<br />
2<br />
V ar(S j ) = σ 2 s = σ 2 e/11.5<br />
The ratio of four times the sire variance to total phenotypic variance (i.e. (σ 2 c + σ 2 s + σ 2 e)), is<br />
known as the heritability of the trait, and in this case is 0.2775. The ratio of the contemporary<br />
group variance to the total phenotypic variance is 0.1329. The important ratios are<br />
σ 2 e/σ 2 c = 6.0<br />
σ 2 e/σ 2 s = 11.5<br />
There are a total of 21 observations, but only five filled subclasses. The individual observations<br />
are not available, only the totals for each subclass. Therefore, an equivalent model is the<br />
“means” model.<br />
ȳ ij = µ + C i + S j + ē ij ,<br />
where ȳ ij is the mean of the progeny of the j th sire in the i th contemporary group, and ē ij is<br />
the mean of the residuals for the (ij) th subclass.<br />
The model assumes that<br />
• Sires were mated randomly to dams within each contemporary group.<br />
• Each dam had only one progeny.<br />
• Sires were not related to each other.<br />
• Progeny were all observed at the same age (or observations are perfectly adjusted for age<br />
effects).<br />
• The contemporary groups were independent from each other.<br />
19