> On average, X is more likely than Y, therefore in any specific case, X is more likely than Y.

I'll take this a bit further. X is more likely than Y so Y is not going to happen & we should not consider Y.

There's a book, recommended by Bill Gates no less, "How to lie with statistics".

From https://en.wikipedia.org/wiki/How_to_Lie_with_Statistics

> Themes of the book include "Correlation does not imply causation" and "Using random sampling". It also shows how statistical graphs can be used to distort reality, for example by truncating the bottom of a line or bar chart, so that differences seem larger than they are, or by representing one-dimensional quantities on a pictogram by two- or three-dimensional objects to compare their sizes, so that the reader forgets that the images do not scale the same way the quantities do.

I'll claim that statistics & even extracting quanta from qualia is going to have data loss from the sampling. So forecasting from statistics requires context on what is being forecasted.