Problems of joint display of species and site scores in correspondence analysis

Joint plots of species and site scores in correspondence analysis can be interpreted so that points which are in the same direction from the origin are closely associated. Species and site scores can thus be compared. Within each set of scores the location of points is also meaningful. Owing to the unimodal species response model which can be recovered by the correspondence analysis, the location of the species points in respect to the site points indicates the location of the optimum when direct weighted averages are used. However, when the eigenvalue of the solution is low, very different joint plots are derived when the set which is used for computing the weighted averages for the other set is changed. This makes the interpretation of the between-set proximities in the joint plot vague. Generally, it is not possible to deduce the species composition of a site or sites where a species occurs from the joint plot, although for some pairs of species and sites this is justified. Although the proximity interpretation is not possible in every case, a joint plot display can greatly enhance the interpretation of results.