(25-01-2019, 08:10 AM)Wladimir D wrote: You are not allowed to view links. Register or Login to view.The main thing is that the values of red columns for different bifolio are very different from each other, but within each bifolio they are not much different. Diagram 7 is averaged over bifolio.
This is the rationale for the first conclusion.
This sounds like an excellent result! A good way to make things clearer could be a histogram with a bar for each page, side by side with the bifolio average. That should show that each single page is close to the bifolio average and different from pages in other bifolios.
I guess that similar results could be obtained with other page-similarity measures, e.g. PCA posted by Donald Fisk You are not allowed to view links. Register or Login to view..
On the other hand, I don't understand why this evidence should rule out the possibility of a simple substitution cipher.