comp.lang.idl-pvwave archive
Messages from Usenet group comp.lang.idl-pvwave, compiled by Paulo Penteado

Home » Public Forums » archive » MPfit question
Show: Today's Messages :: Show Polls :: Message Navigator
E-mail to friend 
Return to the default flat view Create a new topic Submit Reply
Re: MPFIT question [message #64737 is a reply to message #62623] Thu, 15 January 2009 08:17 Go to previous messageGo to previous message
j.coenia@gmail.com is currently offline  j.coenia@gmail.com
Messages: 36
Registered: December 2008
Member
Thanks both of you. I knew it would be something easy for someone. I
was thinking that the lower constraint on t0 in parinfo was good
enough to ensure that the WHERE statement found at least some times
above t0, so that the found count (ct) would never be 0 as Paolo
describes... unfortunately t0 can go all the way down to 0, in which
case ct = n, which leads to the problem Craig describes: there is no
pre-arrival baseline to prepend to the gamma variate if t0 is 0!
Simply changing the GE to GT in the WHERE statement is a quick fix,
but I'll implement better validity checking and MPFIT error trapping
(which I didn't really understand until Craig explained that the
initial MAKE_ARRAY error is being intercepted).

So my code was wrong, but there's nothing theoretically wrong with
trying to fit t0 here, or any piecewise continuous function, using
Levenberg-Marquardt? And my method for guessing error is not
specious? Sorry for the naive questions -- it takes a few days to run
all these fits, so I don't want to do everything wrong from the start.
[Message index]
 
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Previous Topic: Trouble writing very large files
Next Topic: Recording batch commands

-=] Back to Top [=-
[ Syndicate this forum (XML) ] [ RSS ] [ PDF ]

Current Time: Fri Oct 10 15:24:27 PDT 2025

Total time taken to generate the page: 1.28257 seconds