Inf computed by model function, fitting cannot continue.

I have the following data:

x = [0, 1, 2, 3, 4, 5, 6, 7, 8, 9] and y = [1, -0.2213, 0.4189, 0.2125, -0.542, 0, 0, 0, 0, 0]

I'm trying to fit an exponetial curve and even though it is not the best curve to fit, I need it to be exponential. The thing is that it has worked for every single of the other vectors that i have (even for the ones with all-negative values and much worse data) but for some reason the fitting function gives me this error only for this one:

Error using fit>iFit (line 348)

Inf computed by model function, fitting cannot continue.

Try using or tightening upper and lower bounds on coefficients.

Error in fit (line 116)

[fitobj, goodness, output, convmsg] = iFit( xdatain, ydatain, fittypeobj, ...

This is my code:

f = fittype('exp(-x/phi)', 'independent', 'x');

myfit_uu2 = fit(x', y', f, 'StartPoint', 1);

lambda = myfit_uu2.phi;

Answer 1

[Harsha Priya Daggubati]

Hi,

I tried replicating running your code in MATLAB R2019b. I got the result with lamda as 0.0294. No issues as you mentioned.

x = [0, 1, 2, 3, 4, 5, 6, 7, 8, 9];
y = [1, -0.2213, 0.4189, 0.2125, -0.542, 0, 0, 0, 0, 0];
f = fittype('exp(-x/phi)', 'independent', 'x');
myfit_uu2 = fit(x', y', f, 'StartPoint', 1);
lambda = myfit_uu2.phi;

Can you try restarting your MATLAB and using these commands:

rehash toolbox
rehash toolboxcache

Or else try updating to the newer MATLAB versions.

Hope this helps!

[Ivy Gao]

Hi, does this code work on your MATLAB?

baffledTB_x = [0

1.25

2.5

3

3.5

4

18.5];

baffledTB_y = [0.06

0.155

0.289

0.412

0.576

0.641

1.76];

x = baffledTB_x;

y = baffledTB_y;

myfittype = fittype('a + b*log(x)',...

'dependent',{'y'},'independent',{'x'},...

'coefficients',{'a','b'})

myfit=fit(x,y,myfittype,'StartPoint',[0 0.6])

Thanks!!!