model fit comparison matlab

4 ビュー (過去 30 日間)
Ilias Minas
Ilias Minas 2022 年 5 月 30 日
編集済み: Hiro Yoshino 2022 年 5 月 31 日
Hi all,
I have the following graph which shows the raw data of an experiment and the predicted data after executing 2 models.
I would like to compare which model fits better in the raw data.
I tried to use compare and goodnesofffit but the results didnt make sense.
Is there any alternative to this?
  1 件のコメント
Hiro Yoshino
Hiro Yoshino 2022 年 5 月 30 日
編集済み: Hiro Yoshino 2022 年 5 月 31 日
Did you measure the goodness of fit like this?:
mse1 = mean((raw-oneState).^2)


回答 (1 件)

Mathieu NOE
Mathieu NOE 2022 年 5 月 30 日
this is basically waht is called the R² correlation coefficient . If it get's close to 1 it's a good fit, if it get's close to zero there is no fit .
function Rsquared = my_Rsquared_coeff(data,data_fit)
% R2 correlation coefficient computation
% The total sum of squares
sum_of_squares = sum((data-mean(data)).^2);
% The sum of squares of residuals, also called the residual sum of squares:
sum_of_squares_of_residuals = sum((data-data_fit).^2);
% definition of the coefficient of correlation is
Rsquared = 1 - sum_of_squares_of_residuals/sum_of_squares;


Find more on Curve Fitting Toolbox in Help Center and File Exchange

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by