Cj. Brien et Cgb. Demetrio, USING THE RANDOMIZATION IN SPECIFYING THE ANOVA MODEL AND TABLE FOR PROPERLY AND IMPROPERLY REPLICATED GRAZING TRIALS, Australian journal of experimental agriculture, 38(4), 1998, pp. 325-334
A method for deriving the analysis of variance for an experiment is pr
esented and applied to grazing trials. A special feature of grazing tr
ials, specifically utilised by our method, is that they involve at lea
st 2 randomisations: treatments are randomised to field units (for exa
mple paddocks or plots), and field units are randomised to animals. Ra
ndomisation results in the confounding ('mixing up') of terms and our
method includes separate terms in the analysis of variance table for c
onfounded terms so that all sources of variability in the experiment h
ave terms for them included in the table and the confounding between t
he sources of variability in the experiment is explicitly displayed in
the table. This information is used in determining the valid error te
rms and we will present examples that show how to ascertain these for
effects of interest and hence which effects can be tested. In this it
fulfils the same role as the contentious process of identifying the ex
perimental unit. It will be demonstrated that the inclusion of separat
e terms for confounded terms results in improper replication in grazin
g trials being automatically signalled, and makes its ramifications cl
ear.