Re: Re: NonlinearRegress of user functions

*To*: mathgroup at smc.vnet.net*Subject*: [mg91558] Re: [mg91534] Re: NonlinearRegress of user functions*From*: Lai Ngoc Anh <anhngoclai at yahoo.com>*Date*: Wed, 27 Aug 2008 06:42:52 -0400 (EDT)

Dear Jean-Marc, Dear All, You are right that parameter A, B, C, D, E should be lowercase or longer name. In order to shorten long parameters for the discussion, I write 5 parameters in single capital letter, A, B, C, D, E. In practice the parameters is longer and module psT[Texp,pA, pB, pC, pD, pE] and rhocal = rhoT[Texp, pA, pB, pC, pD, pE] run perfectly. The problem for me is that I can not find out correct 5 parameters by using NonlinearRegress or NMinimize to fit the experimental data. May be I need to use other commands or modify my syntax or procedure or manipulation... to solve the problem. I would appreciate if you or anyone can help me to solve the problem. Thanks and regards, Lai Ngoc Anh ----- Original Message ---- From: Jean-Marc Gulliet <jeanmarc.gulliet at gmail.com> To: mathgroup at smc.vnet.net Sent: Monday, August 25, 2008 11:57:04 AM Subject: [mg91558] [mg91534] Re: NonlinearRegress of user functions Ngoc Anh Lai wrote: > I have experimental data set of (Texp, pexp, rhoexp). With each value of > Texp, I will calculate pcal and rhocal by using functions pcal = psT[T, > A, B, C, D, E] and rhocal = rhoT[T, A, B, C, D, E]. Parameters A, B, C, > D, E of the functions psT and rhoT will be found by Minimization of <snip> FWIW, though I cannot tell for sure whether this is the source of your problems, note that, in general, it is a very bad idea to use single capital letters as names of variables because many of them have already been attributed some predefined meanings (every Mathematica built-in command begins with a capital letter). For instance, D is the differential operator, E is the base for natural logarithms. You should use longer names and/or start them with lowercase letters. Regards, -- Jean-Marc