[SciPy-user] Using SciPy/NumPy optimization

[Brandon Nuttall]

Folks,

The usual confessions: I am relatively new to Python programming and SciPy. 
I have a problem I'm looking for some help in solving.

I have a list of data pairs [[x1,y1], [x2,y2], ..., [xn,yn]] and am trying 
to find the best fit of that data to an equation:

      y = a*(1+b*c*y)^(-1/b)

The parameters, b and c, are constrained:
      1) 0<b<=5
      2) -1<=c<=1

Parameter a is only weakly constrained in that x is usually >= max(x1, x2, 
... , xn).

My "best fit" goal is either to minimize the root mean square deviation (or 
consequently maximize the r-square value).

Any suggestions?

Thanks.



Brandon C. Nuttall

BNUTTALL at UKY.EDU                         Kentucky Geological Survey
(859) 257-5500                                     University of Kentucky
(859) 257-1147 (fax)                              228 Mining & Mineral 
Resources Bldg
http://www.uky.edu/KGS/home.htm       Lexington, Kentucky 40506-0107