Rh. Green, APPLICATION OF REPEATED-MEASURES DESIGNS IN ENVIRONMENTAL-IMPACT AND MONITORING STUDIES, Australian journal of ecology, 18(1), 1993, pp. 81-98
Traditional environmental studies have employed sampling at different
times, but based on re-randomized 'replicate' samples taken at each ti
me. For example, in a 4 year monitoring study of near-shore marine ben
thic communities there might be three box cores collected annually at
each of three depths along each of three transects. Repeated measures
designs, long used in medicine and the social sciences, are based on r
esampling replicates (e.g. sites) at a series of times. In such design
s spatial sampling variability is not used for tests of environmental
impact. Error for such tests is based on variability of time trends am
ong similar sites (similar with respect to impact). For example in a t
ropical oil spill study five oiled and five unoiled coral reefs were s
tudied over 5 years. Error for tests of oil impact was based on variab
ility among reefs (within degree-of-oiling category) in the year-to-ye
ar trends of biological response variables. It was not based on variab
ility among field samples within reefs at given times. The two approac
hes (univariate and multivariate) to repeated measures analysis of var
iance are described. The pros and cons of each are discussed, as are t
he assumptions and consequences of their violations. Emphasis is espec
ially placed on the adequacy of error degrees of freedom in the two ap
proaches, and some exploration of power to detect impact is presented.
Examples of application of repeated measures designs to various impac
t and monitoring studies are presented and discussed, including (i) in
terpretation of significant effects; (ii) decomposition of effects by
contrasts (e.g. before vs after impact); and (iii) modelling time tren
ds by polynomial and cosine functions.