The whole purpose of the "Scientific Method", where you establish a testing method, conduct the test, and publish your results for peer review, is so any potential errors are found and can be discussed.
If an error is found, then the so called "proof", isn't really "proof", and you have to go back to the drawing board. It doesn't mean you're theory was necessarily wrong, it just means that the data isn't valid.
In other words, this is the whole reason we discuss this issues. Don't get upset if someone doesn't agree with your test method.
------------------
Vermillion
**MOL**, Men of Leisure