How to do parameter fitting for a system of equations with 3 independent variables?
18 views (last 30 days)
Show older comments
I have a system of 3 equations with 3 independent variables( x1,x2,x3) and correspondingly 3 dependent variables( y1,y2,y3) as follows:
- y1=((b1*x1)/(1+(b1*x1)+(b2*x2)+(b3*x3))) + ((b4*x1)/(1+(b1*x1)+(b2*x2)+(b3*x3)));
- y2=((b2*x2)/(1+(b1*x1)+(b2*x2)+(b3*x3))) + ((b5*x2)/(1+(b1*x1)+(b2*x2)+(b3*x3)));
- y3=((b3*x3)/(1+(b1*x1)+(b2*x2)+(b3*x3))) + ((b6*x3)/(1+(b1*x1)+(b2*x2)+(b3*x3)));
x and y data are available.
I need to fit 6 parameters( b1,b2,b3,b4,b5,b6) in this system.
I tried using nlinfit but couldn't make it work for this case. Suggest me how to solve this problem. Thank you.
0 Comments
Accepted Answer
Torsten
on 18 Aug 2015
Edited: Torsten
on 18 Aug 2015
xdata = horzcat(x1,x2,x3);
ydata = horzcat(y1,y2,y3);
fun=@(b,xdata) horzcat((b(1)+b(4))*x1./(1+b(1)*x1+b(2)*x2+b(3)*x3),(b(2)+b(5))*x2./(1+b(1)*x1+b(2)*x2+b(3)*x3),(b(3)+b(6))*x3./(1+b(1)*x1+b(2)*x2+b(3)*x3));
b0=[1 ; 1 ; 1 ; 1 ; 1 ; 1];
[x,resnorm] = lsqcurvefit(fun,b0,xdata,ydata);
Best wishes
Torsten.
1 Comment
Amaya
on 25 May 2017
I tried doing this on a similar problem and the extimated x output changes with the initial guess, even when setting a very low tolerance:
% code
opts = optimset('TolX',1e-15);
[vestimated,resnorm] = lsqcurvefit(fun,x0,xdata,ydata,[],[],opts);%
how does lsqcurvefit pass x1,x2 and x3 into fun?, shouldn't fun be expressed in terms of
xdata(initial_index:final_index).
rather than in terms of x1,x2 and x3?
Thanks
More Answers (1)
See Also
Categories
Find more on Least Squares in Help Center and File Exchange
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!