If you are into the whole field of statistics, you won't want to miss Stephen Carlson's blog entries on Lukanisms and Mattheanisms. It's interesting reading, but one has to be very careful when it comes to interpreting the data. IMO, the use of distinctive or frequent words to try to establish literary dependence is problematic, at best. It would be nice to know what "tool of the trade" Stephen made use of in order to collect the data... hint, hint...