How could you prove that VM is gibberish?

[dashstofsk]

But my feeling is that these statistical methods won't give 100% answer it the text is meaningful or not.

Statistics never gives 100% proof. Hypothesis testing is about obtaining confidence levels. i.e. a confidence level of 95% that some observed effect cannot be down to randomness.

In the case of the VMS it can be difficult to try to use statistical hypothesis testing to give a definite answer to whether the text is meaningful or not. The text is a product of human endeavour and so most likely the writers ( the general belief being that there were more than one ) would have written in their personal and distinct styles, choosing to write with more carefulness on some days, in more of a hurry, with abandon on other days, being in a jocular mode on others. Each writer had a free hand to write what he liked. All this makes it difficult to know how best to apply statistics.

The role of statistics is not to prove but to provide evidence to tilt opinion towards a hypothesis. Instead of aiming for 100% proof search for what is logical, plausible.

If you are asking for ways that may suggest that the text is meaningless then one way would be to look for evidence of artificial construction. People have noted within the text long distance effects, vertical pair effects, and other anomalies that cannot be explained if the text were a continuous narrative in a natural language. These effects cannot easily be dismissed. May I trouble you also to read my post on splitting gallows words

You are not allowed to view links. Register or Login to view.

which shows that the initial and final word parts of gallows words are independent and likewise unlikely to be in a natural language. Hopefully this piece of evidence might tilt your opinion towards the hypothesis that the text is meaningless, a hoax.