Binomial distribution in VMS

[nablator]

Where did Stolfi make such a statement ?

Figure 1 - Token length distributions.
Figure 2 - Word length distributions.
Figure 3 - Voynichese word length distribution, compared to the binomial one.

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

It is clearly the word [types] length distribution that is matched to the binomial one, i.e. the distribution of "distinct VMS words of each length, ignoring their frequencies in the text".

You used the length of words in EVA (by Takeshi Takahashi) and Stolfi did not so it's not surprising that you got different results.

Congratulations.