Hi, all,
I wrote a technical report on mathematical details at implementational level behind the parameter generation (PG) tool HMGenS. Three cases of PG are all illustrated, including Cholesky decomposition based PG, EM based PG, and PG considering global variance (GV). Three possible tiny errors in the original GV literature are also pointed, and the possibility of closed form solution to PG considering GV is discussed briefly.
This report is directly available from
http://www.escience.cn/system/file?fileId=70185 It can also be found on my homepage
http://www.escience.cn/people/yangwang I hope some of you will find it to be useful. Any comments/corrections are highly welcome.
Thanks a lot!
Yang Wang