Testing for pure specification bias by adding the variances of the LGA mean THM concentrations to the models reduced the IRRs in men somewhat but had little effect on women (Table 3).
Fluxes were approximated by dividing differences in two concentrations by the experiment time (4 hours), and standard errors for fluxes were derived by adding the variances of the two concentration measurements.
Estimates of the individual log variances associated with each of the eight variables are developed from a regression model based on the assumptions of log normality and that the total variance can be obtained by adding the variances associated with each individual variable (Hattis et al. 1999).
In a second step, the clean likelihood (p(mathbf {x}_{n}|q_{n} phantom {dot {i}!}) is evaluated at (boldsymbol {mu }_{mathbf {x}|mathbf {y}_{n},q_{n}}phantom {dot {i}!}) after adding the variance (mathbf {C}_{mathbf {x}|mathbf {y}_{n},q_{n}}phantom {dot {i}!}) to (mathbf {C}_{mathbf {x}|q_{n}}phantom {dot {i}!}), cf. (36).
The total variance was calculated by adding the variance of each stratum.
The phenotypic variance was obtained subtracting the "true" residual variance from the pseudo-error variance estimate and adding the variance of the permanent environmental effect of the cows used in the routine genetic evaluation (S Fritz, UNCEIA, Jouy-en-Josas, personal communication), which was not estimable in our data because our DYD are "free" of permanent environmental effects.
This is because when extra variables are added, the variances are confounded, i.e. changes in variance of the residuals at one level induce changes in variance of residuals at another level (Kreft and de Leeuw 1998).
We added the variance-controlling loci to the loci found to have significant marginal effects by Bloom et al. (2013).
When postnatal depression was added the variance increased by another 11% and again improved the model fit significantly, (F(13, 143) = 9.79, p <.001).
Before the weekly variations were added, the variance in the liabilities (~ N 0, 0.8)) was chosen to give a mastitis heritability of 0.1, which is in line with what is normally found in cross-sectional linear models (on the underlying scale) [ 5, 37, 38].
Variances for the interference profiles were obtained by adding the scaled variances of the constituent profiles.
