I am a new user of MATLAB and have the "CURVE FITTING" Toolbox. However, it is limited to multiple regression models of only 3 variables. What if you have more than 3 variables? Also, can MATLAB deal with nonlinear regression? If so, please provide me with the proper syntax for either or both cases. Thank you.
As far as I know it's limited to only 3 variables. You can use the fourth data series as weight, but not as a variable.
Dear Prof. Amir W Al-Khafaji,
Why are you using MATLAB for multiple regression models? There are other user friendly softwares namely R, Python, SPSS, Weka etc. to perform multiple regression models. I think these softwares are vey helpful. Thanks.
Dear Mr. Amin, MATLAB has a great graphics interface and works on the MAC. I am a Macintosh user! Amir
Dear Sk Abdul Amin - I use natlab because it is s powerful platform that offers exceptional graphic interface, eigenproblems, etc. it is more efficient to master one apllication than switch between several. Amir
yes you can do it in Matlab,
check this example (with 2 variables), you can make an example with 3 or more.
x1 = [1 2 3 4 5 6]';
x2 = [.2 .4 .8 .9 1.1 2.1]';
X = [x1 x2]; % independent variables
f = [ 3.3079 6.6358 10.3143 13.6492 17.2755 23.6271]';
objfcn = @(A,X)A(1)*x1 + x2.^(A(2));
x0=1; %Algo needs an initial random solution
x0=(1)*[1;1];
[vestimated,resnorm] = lsqcurvefit(objfcn,x0,X,f)
- Badges
- Science topic