MATLAB Answers

Error in optimization process

6 views (last 30 days)
Fred
Fred on 4 Oct 2013
Edited: Matt J on 4 Oct 2013
I am trying to fit a gumbel distribution on a series of data. So I want to minimize the negative of maximum likelihood by optimizing two variables var(1) and var(2). This is my code:
X=xlsread('file.xlsx');
options = optimset('MaxFunEvals',1000,'FinDiffType','central');
options=optimset(options,'Display','iter','MaxIter',1000,'TolCon',1e-6);
lb=0;
ub=Inf;
var=zeros(2,1);
x = fmincon(@(var)Gumbel(var,X),1,1,[],[],[],[],lb,ub,[],options);
and my Gumbel function is:
function f=Gumbel(var, X)
f=-sum(log((1./var(1)).*exp(-(X-var(2))./var(1)-exp(-(X-var(2))./var(1)))))
Can someone help me why I am getting errors?! Thanks

  2 Comments

Shashank Prasanna
Shashank Prasanna on 4 Oct 2013
What are you errors? Can you post it here?
Fred
Fred on 4 Oct 2013
Error using fmincon (line 294)
Row dimension of A is inconsistent with length of b.
Error in LL (line 10)
x = fmincon(@(var)Gumbel(var,X),1,1,[],[],[],[],lb,ub,[],options);

Sign in to comment.

Accepted Answer

Matt J
Matt J on 4 Oct 2013
Edited: Matt J on 4 Oct 2013
Your input arguments are out of sequence. Also, you have too many of them. fmincon can only accept 10 inputs and you've passed in 11.

  0 Comments

Sign in to comment.

More Answers (0)

Sign in to answer this question.


Translated by