Canonical correspondence analysis (CCA) is suited to response data that is unimodally distributed relative to some environmental gradient expressed in a matrix of explanatory variables. CCA uses the explanatory matrix to constrain the execution of a correspondence analysis (CA) and only presents correspondence that can be 'explained' by your explanatory variables. Significance tests are available to assess whether the relationship between the response and explanatory data are stronger than can be expected by chance.
Click here to find out more...