There are many other issues that one can raise about the statistical
analysis. For example, it was not a random sample; we identified one
kind of selection bias. So the statistical analysis is only about the
sample itself, not about some hypothetical population of ontologies
(whatever that would be).
since this is not a random sample, it is hard to understand the import of the data without knowing a bit about the sample itself.
you mentioned these are large ontologies, what do you mean exactly?
could you say something more on the criteria you used to select the ontologies?