Gordon, we've established that you think the Bristol team are good
scientists and upstanding human beings.  We've defined "conjecture" and
have been treated to an essay on the scientific method.

I'll ask you again for the one thousandth time.  What do you plan to do
with the question at hand?  Are you prepared to dismiss the results of the
study as a statistical anomaly?  Do you find compelling the conjecture
that non-drinking ill people comprise a subset of the nondrinking
population thereby flattening the left hand side of the curve?