Data tables of descriptors

Assume that the set of potential test compounds contains N different compounds. Assume also that each compound has been characterized by K different descriptors. 

The same descriptors have been used to characterize all compounds. The data can be summarized in a table, a (NxK) matrix in which the columns correspond to the K descriptors, and the rows correspond to the N different compounds, see Fig. 15.1. 

It is necessary to resist the temptation to analyze tables like the one below by considering one variable at a time. The risk of finding spurious correlations between the variables increases rapidly with an increasing number of variables. If we wish to be sure at a probability level of 95 % that a descriptor variable is correlated to a chemical penomenon, this also means that we accept a risk of 5 % that this variable is by pure chance correlated to the phenomenon. This risk with k variables will be 

Analysis of data tables with several variables must be made by means of 

---