How Calculate R squared from a linear regress

Question

Nicholas Deosaran 2020-9-29

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/602089-how-calculate-r-squared-from-a-linear-regress

回答： Star Strider 2020-9-29

采纳的回答： Star Strider

在 MATLAB Online 中打开

Hey all I have this equation below and trying to figure out how to get the R^2.

I can't seem to understand what I am doing wrong.

x = 0:0.1:10;
n = 0;
noise = n*rand(1,length(x));
y = 2*x+1+noise; % y function 
b = regress(y(:),[ones(size(x(:))),x(:)]); % get the intercept and slope
figure();
plot(x,y,'d') %plot as diamonds
hline = refline(b(2),b(1)); % plot the liner regresson line
hline.Color = 'r'; % change linear regresson line to red 

I have looked at different ways in MATLAB but can't seem to understand.

Thank you.

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 2020-9-29

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/602089-how-calculate-r-squared-from-a-linear-regress#answer_502534

在 MATLAB Online 中打开

They are hidden in the ‘stats’ output:

[b,~,~,~,stats] = regress(y(:),[ones(size(x(:))),x(:)]); % get the intercept and slope
Rsq = stats(1)
Rsq_p = stats(3)
Fstat = stats(2)
ErrVar = stats(4)

Even the documentation is not straightforward with disclosing which outputs are those it mentions. This is my best effort as to deciphering them. (I am certain that the first two are correct, based on my reading of the documentation.)