fminsearch for ligistic fit

Question

Mona Berg 2020-5-28

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/536267-fminsearch-for-ligistic-fit

评论： Mona Berg 2020-6-2

I'm trying to use fminsearch to fit a logistic model to my data. My problem is that I'm rreally confused about how to define the input for the fminsearch function.

My data:

x = [0.5 2.7 6 8.8 9.7 12.8 16 20 23];
y = [0.8 1.1 3.4 7 9 13 13.4 13.2 18.8];

I want to fit the parameters of following function to my data:

Now I don't know how to define the right functions for the optimization.

What I've tried so far:

f = @(p,x)p(1)*(0.5-(1./(1+exp(p(2)*(x-p(3))))))+p(4)*x+p(5);
f2 = @(p)f(p,x);   
p0 = [0.1 0.1 0.1 0.0001 0.1];
p = fminsearch(f2,p0); 

But this is not the right way.

0 个评论
显示 -2更早的评论隐藏 -2更早的评论

请先登录，再进行评论。

请先登录，再回答此问题。

Answer 1

Walter Roberson 2020-5-28

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/536267-fminsearch-for-ligistic-fit#answer_441163

在 MATLAB Online 中打开

f2 = @(p)f(p,x);

That relies on x existing in your workspace. If you are going to do that you might as well assume it on the previous line, and use cleaner code.

But your bigger problem is that you are failing to calculate a sum-of-squared errors

f = @(p) p(1) * (0.5 - (1 ./ (1 + exp(p(2)*(x-p(3)))))) + p(4) .* x + p(5);
f2 = @(p) sum((f(p) - y).^2);
p0 = [0.1 0.1 0.1 0.0001 0.1];
p = fminsearch(f2, p0); 