Non linear least squares regression

Hi All,

I am pretty new to MATLAB and am trying to perform a non-linear least squares regression on a vector of residuals generated from the equation:

AT+(ST/(1+(Ks*Z)/(f*H'))+(FT/(1+Kf/(f*H'))+((mo+m)/mo)*(f*H'/Z)-(m/mo)*C=0

where AT, ST, Ks, Kf, Z, FT, mo, & C are all values and f, H', & m are all vectors

I need to perform the regression by adjusting AT (a value) and f (a vector). Then I need to output the adjusted values of AT & f.

I've looked around, but I can't figure out how to do it.

Any help would really be appreciated. Thanks.

David

Answer 1

[the cyclist]

If you have the Statistics Toolbox, you should be able to do this with the nlinfit() function.

[David]

thanks. but i don't know how to code it correctly. it seems like it should be straightforward, but i can't seem to figure it out. any ideas?

[David]

more specifically, I don't understand the syntax for the nlinfit function. For my example, I can't figure out what X, Y, Modelfun, and beta should all be.

[the cyclist]

I can't code your function for you, but here is a simple example I made for myself some time ago, to test a very simple quadratic fitting. Maybe it will help you figure it out.

function [] = nlinfitExample()

% Define the data to be fit

x=(0:1:10)'; % Explanatory variable

y = 5 + 3*x + 7*x.^2; % Response variable (if response were perfect)

y = y + 2*randn((size(x)));% Add some noise to response variable

% Define function that will be used to fit data

% (F is a vector of fitting parameters)

f = @(F,x) F(1) + F(2).*x + F(3).*x.^2;

F_fitted = nlinfit(x,y,f,[1 1 1]);

% Display fitted coefficients

disp(['F = ',num2str(F_fitted)])

% Plot the data and fit

figure(1)

plot(x,y,'*',x,f(F_fitted,x),'g');

legend('data','nonlinear fit')

end