User`s guide

fit

4-105

Example Fit the census data with a second-degree polynomial library model and return

the goodness of fit statistics and the output structure.

load census

[fit1,gof1,out1] = fit(cdate,pop,'poly2');

Normalize the data and fit with a third-degree polynomial.

[fit1,gof1,out1] = fit(cdate,pop,'poly3','Normalize','on');

Fit the data with a single-term exponential library model.

[fit2,gof2,out2] = fit(cdate,pop,'exp1','Normalize','on');

Create a fit options object, and try to find a better fit by overriding the default

starting points for the fit coefficients.

opts = fitoptions('exp1','Norm','on','start',[100 0.1]);

[fit3,gof3,out3] = fit(cdate,pop,'exp1',opts);

Fit the data to a custom model that contains the problem parameter n.

mymodel = fittype('a*exp(b*n*x)+c','problem','n');

opts = fitoptions(mymodel);

set(opts,'normalize','on')

[fit4,gof4,out4] = fit(cdate,pop,mymodel,opts,'problem',{2});

Warning: Start point not provided, choosing random start point.

The warning occurs whenever you fit data with a custom nonlinear model and

do not provide starting points.