Error message using function fminunc

Hi, I'm using the function fminunc to find my least square error. Unfortunately I get the error message

      Error using fminusub (line 16)
      Objective function is undefined at initial point. Fminunc cannot continue.

      Error in fminunc (line 457)
         [x,FVAL,GRAD,HESSIAN,EXITFLAG,OUTPUT] = fminusub(funfcn,x, ...

I understand the error can be caused by an inf or nan value, however I don't this applicable to me (??). My program for generation born 1938 looks like (the other generations result in same error message):

fun_1938=@(param)f_Makeham(param, mu_perks_1938, 1938);
param0_1938 = [2.06441912000572E-07/1000,0.197642212387667/100000,1.23947876070978/10];
[param_1938, fval_1938]=fminunc(fun_1938,param0_1938);

where

function res = f_Makeham(param,mu_perks,year)

a0=param(1);
b0=param(2);
c0=param(3);

if year == 1938
    x=(77.5:1:106.5)';
elseif year==1945
    x=(70.5:1:106.5)';
elseif year==1955
    x=(65.5:1:106.5)';
end
res=sum((a0+b0*exp(c0*x)-mu_perks).^2);

What is causing the error message? How can I error track this?

[Walter Roberson]

Possibly mu_perks_1938 is not defined.

Answer 1

[Alan Weiss]

The error is clear. Try to evaluate fun_1938(param0_1938) and you will find that it throws an error. Investigate the error using standard MATLAB debugging.

Alan Weiss

MATLAB mathematical toolbox documentation

[Orongo]

I'm trying to do this but not getting anywhere.