The point of the algorithm is not to figure out if Moses or whoever wrote the bible. The point is to track down strands of a multi-author book:

The new software analyzes style and word choices to distinguish parts of a single text written by different authors, and when applied to the Bible its algorithm teased out distinct writerly voices in the holy book.

The program, part of a sub-field of artificial intelligence studies known as authorship attribution, has a range of potential applications — from helping law enforcement to developing new computer programs for writers. But the Bible provided a tempting test case for the algorithm's creators.

I studied this sort of thing a little from the Humanities side in graduate school, and it can be fascinating. But a lot of room is still left for interpretation and other factors. One example: Caesar's war diaries in Gaul show significant shifts in vocabulary, word order, sentence structure and narrative style between the early and later books. In that case though, multiple authorship is much less likely than one author changing over time. This sort of thing would probably make it harder to solve the Shakespeare problem using this software (which someone mentions as a use case in the article).

http://languagelog.ldc.upenn.edu/nll/?p=3233