One type of ideal design is illustrated in Fig. 1.11 and the analysis is shown
in Tables 1.2 and 1.3. The situation concerns the construction of sewage outfalls
along a coastline. They are to be situated on rocky headlands with fast currents,
deep water and coarse offshore sediments. Two outfalls were examined, with two
corresponding control areas with similar features of habitat (rocky headlands with
fast currents, deep water and coarse sediments). Any coast-wide change in benthic
fauna that is not due to discharge of sewage will affect the control areas and the
outfall locations. An impact will cause a different type of change where there
are outfalls from where there are no outfalls (hence an interaction in the spatial
difference between outfall and control locations from before to after the outfalls
are commissioned).
Data are collected three times (essentially chosen at random) over two years
before the outfalls begin to discharge sewage and then three times over a period
of two years, starting two years after the outfalls are commissioned (Fig. 1.11). At