Ml. Gumpertz et C. Brownie, REPEATED-MEASURES IN RANDOMIZED BLOCK AND SPLIT-PLOT EXPERIMENTS, Canadian journal of forest research, 23(4), 1993, pp. 625-639
Randomized block and split-plot designs are among the most commonly us
ed experimental designs in forest research. Measurements for plots in
a block (or subplots in a whole plot) are correlated with each other,
and these correlations must be taken into account when analyzing repea
ted-measures data from blocked designs. The analysis is similar to rep
eated-measures analysis for a completely randomized design, but test s
tatistics must allow for random block x time effects, and standard err
ors for treatment means must also incorporate block to block variation
and variation among plots within a block. Two types of statistical an
alysis are often recommended for repeated-measures data: analysis of c
ontrasts of the repeated factor and multivariate analysis of variance.
A complete analysis of repeated measures should usually contain both
of these components, just as in univariate analysis of variance it is
often necessary to decompose the main effects into single degree of fr
eedom contrasts to answer the research objectives. We demonstrate the
multivariate analysis of variance and the analysis of contrasts in det
ail for two experiments. In addition, estimation of coefficients assum
ing a polynomial growth curve is discussed in detail for one of these
experiments. The first experiment, a randomized complete block design,
is a forest nutrition study of the long-term effects of midrotation n
itrogen and phosphorus fertilization on loblolly pine (Pinus taeda L.)
; the second experiment, a split-plot design, is an air-pollution stud
y of the effects of ozone and acid precipitation on loblolly pine grow
th.