how to find parameter heligman pollard model
Info
This question is closed. Reopen it to edit or answer.
Show older comments
i have question to every body....this is my project in college.. i have a problem about non-linear least square..and i working in matlab.. i have data
x1=[0;1;5;10;15;20;25;30;35;40;45;50;55;60;65;70;75];
ydata=[0.00859 0.001714 0.001466 0.001308 0.00381 0.005388 0.005978 0.00673 0.009336 0.014156 0.021598 0.034274 0.05383 0.08526 0.136546 0.21604 0.329148];
and my function is..
y=((b1.^((x+b2).^b3))+(b4.*exp(-b5.*(log(x./b6)).^2))+(b7.*(b8.^x)))/(1+((b1.^((x+b2).^b3))+(b4.*exp(-b5.*(log(x./b6)).^2))+(b7.*(b8.^x))));
how to find parameter
b1,b2....b8????
and i have been try it..to find parameter b1,b2....b8..this is my m.file
syms x y b1 b2 b3 b4 b5 b6 b7 b8 real
yduga=((b1.^((x+b2).^b3))+(b4.*exp(-b5.*(log(x./b6)).^2))+(b7.*(b8.^x)))/(1+((b1.^((x+b2).^b3))+(b4.*exp(-b5.*(log(x./b6)).^2))+(b7.*(b8.^x))));
r=y-yduga;
J=[diff(r,b1) diff(r,b2) diff(r,b3) diff(r,b4) di...ff(r,b5) diff(r,b6) diff(r,b7) diff(r,b8)];
c1(1)=?
c2(1)=?
c3(1)=?
c4(1)=?
c5(1)=?
c6(1)=?
c7(1)=?
c8(1)=?
for i=2:10
t=[c1(i-1) c2(i-1) c3(i-1) c4(i-1) c5(i-1) c6(i-1) c7(i-1) c8(i-1)]
xdata=[1 5 10 15 20 25 30 35 40 45 50 55 60 65 70 75];
ydata=[0.001714 0.001466 0.001308 0.00381 0.005388 0.005978 0.00673 0.009336 0.014156 0.021598 0.034274 0.05383 0.08526 0.136546 0.21604 0.329148];
rr=subs(r,{b1 b2 b3 b4 b5 b6 b7 b8},[t]);
rrr=subs(rr,{x y},{xdata ydata});
JJ=subs(J,{b1 b2 b3 b4 b5 b6 b7 b8},[t]);
JJJ=subs(JJ,{x},{xdata});
d=inv(JJJ'*JJJ)*(-1)*JJJ'*rrr;
beta=plus(t',d)
c1(i)=beta(1)
c2(i)=beta(2)
c3(i)=beta(3)
c4(i)=beta(4)
c5(i)=beta(5)
c6(i)=beta(6)
c7(i)=beta(7)
c8(i)=beta(8)
end
i using Gauss-newton method, but until this time i can't find parameter b1,b2..b8..maybe my problem is about starting value, but i dont know....?? i hope u all can help me thanks a lot....
1 Comment
Matt Fig
on 5 Apr 2011
Please format your code.
Answers (0)
This question is closed.
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!