Dinosaur Wrote:know if Baysian analysis can be used on OSL/TRM data etc (ie other dating techniques that produce statistical date ranges) and if so whether data from different techniques can be combined? - have a nightmare job where am going to get some OSL or C14 and occasional strat relationships, but not too many of any individual type, and pretty much no dateable finds unless things take a sudden turn for the better, but the possibility of some clever maths might affect what/how to dig
I'm no expert and there are probably others who understand this method far better. From what I do understand Baysian Stats in this case was used to tighten up 14c calibration. Dr. Bayliss was using seriation in conjuction with Baysian calibration. The seriation was based on a very robust data set and was tested statistically for reliability. If your interested in more information on Baysian Calibration have a look this site: http://bcal.shef.ac.uk/top.html
Perhaps you might want to consider scaling down your approach? MS Access is fab for database and SPSS is a good stats package. For other than calibrating, try testing your data with NPAR, Chi Square, Frequency and Probability tests for reliability. I had good results using these stats for analysing lithic data through stratum and accross site locations. There are some good books geared for archaeologists and stats, and maths were never my strongest suit. The books were a huge help. As for testing your data, test like for like first, then look at the results in comparison:face-approve:
A positive attitude may not solve all your problems, but it will annoy enough people to make it worth the effort.