Dear Agnes,
I came across that problem straight away when starting with SPM5. Fortunately, it's a known Matlab-issue (so no blame on the SPMers ;-)):
See this mailing list by "search the archive"
svd NaN
and look for an e-mail Andreas Bruns wrote in May:
"Solution for ReML estimation error (NaN in svd) in SPM5, MATLAB 7"
Or go to this Matlab page
http://www.mathworks.com/support/solutions/data/1-18QUC.html?solution=1-18QUC
directly.
Kind regards,
Lars Kasper
--
visiting student
c/o
Dr Michael Breakspear
Senior Research Fellow
The Black Dog Institute
Hospital Road
Randwick NSW 2031
--
"Ein Herz für Kinder" - Ihre Spende hilft! Aktion: www.deutschlandsegelt.de
Unser Dankeschön: Ihr Name auf dem Segel der 1. deutschen America's Cup-Yacht!
|