Mj. Anderson et Na. Gribble, PARTITIONING THE VARIATION AMONG SPATIAL, TEMPORAL AND ENVIRONMENTAL COMPONENTS IN A MULTIVARIATE DATA SET, Australian journal of ecology, 23(2), 1998, pp. 158-167
We propose a method of partitioning the variation in a multivariate se
t of data according to (i) environmental variables, (ii) variables des
cribing the spatial structure in the data and (iii) temporal variables
. This method is an extension of an existing method for partialling ou
t the spatial component of environmental variation, using canonical an
alysis. Our proposed method extends this approach by including tempora
l variables in the analysis. Thus, the partitioning of variation for a
data matrix of species' abundances or biomass can include, by our met
hodology, the following components: (1) pure environmental, (2) pure s
patial, (3) pure temporal, (4) pure spatial component of environmental
, (5) pure temporal component of environmental, (6) pure combined spat
ial/temporal component, (7) combined spatial/temporal component of env
ironmental and (8) unexplained. In addition, permutation testing accom
panying the analyses allows tests of significance for the relationship
between the different components and the species data. We illustrate
the method with a set of survey data of penaeid species (prawns) obtai
ned on the far northern Great Barrier Reef, Australia. This extension
is a useful tool for multivariate analysis of ecological data from sur
veys, where space, time and environment commonly overlap and are impor
tant influences on observed variation.