How to do regression between three inputs (x1, x2 and x3) and one outputs (y) using Curve Fitting?

Question

Radek 2015-6-8

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/222949-how-to-do-regression-between-three-inputs-x1-x2-and-x3-and-one-outputs-y-using-curve-fitting

评论： Star Strider 2015-6-9

How to do regression between three inputs (x1, x2 and x3) and one outputs (y) using Curve Fitting? The Cuve fittinng show only regression between x1, x2 inputs and z outputs

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

Star Strider 2015-6-8

1
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/222949-how-to-do-regression-between-three-inputs-x1-x2-and-x3-and-one-outputs-y-using-curve-fitting#answer_181965

在 MATLAB Online 中打开

I don’t have the Curve Fitting Toolbox (Statistics and Optimization instead), so I can’t address the Curve Fitting Toolbox specifically. However it is straightforward to do this with the other functions, by combining the three vectors into one matrix, then addressing them appropriately in your objective function:

x123 = [x1(:),  x2(:),  x3(:)];
y    = [column vector with the same row size as ‘x123’];
f    = @(b,x) b(1).*x123(:,1).^b(2) + b(3).*x123(:,2) + x123(:,3);    % Example Objective Function
B0   = [choose vector of initial parameter estimates];
B = nlinfit(x123,y,f,B0);               % Estimate Parameters

You will have to experiment with the Curve Fitting Toolbox, but since it can use custom objective functions, something like this should work.