Where significant F-values were observed, we tested for differences within model effects by the Tukey honest significant difference test (12 ).
Further, learning in the Bayesian model of belief is effected by conditionalisation.
There have been some attempts in the Yakopcic and TEAM/VTEAM models to model this effect by setting the value of f2 = 0 within a certain voltage range.
The Weisberg and Zheng [34] formulation used in this paper models this effect by cutting off the Large and Pond [35] increase at 25 m/s.
Therefore, modeling genetic effects by including imprinting effects is expected to improve the predictive ability of GBLUP.
Because the three variables of age, period and cohort were originally continuous, we modelled these effects by parametric smooth functions.
We modelled the effect by income considering the main potential drivers of differences between income groups (price responsiveness, baseline consumption of sugar sweetened drinks, and prevalence of obesity).
Plausible model effects can be forced by setting conditions such as monotonicity, convexity, concavity or combinations thereof.
In a combined model, effects of interaction were examined by the inclusion of interaction terms.
We tested the null hypotheses of multiplicative gene-gene interactions by evaluated departures from multiplicative joint effect models by including main effect variables and their product terms in the logistic regression model [ 15].
