How to calculate R-square using robust linear regression function

5 次查看（过去 30 天）
jalcaraz
jalcaraz 2012-11-29
回答： Christian 2015-5-19
In the linear regression function (regress), one may get the R^2 value directly from one of the 'stats' variable in [b, bint, r, rint, stats] = regress(y,X) function
I want to do a robust linear regression with [b,stats] = robustfit(X,Y)
However, I can't find in the help panel how to assess R^2 from the output variables of the 'robustfit' function.
Any help will be very welcome
JA

请先登录，再回答此问题。

回答（2 个）

Matt Fig
Matt Fig 2012-11-29
[brob, rob_stats] = robustfit(x,y);
rsquare = corr(y,brob(1)+brob(2)*x)^2
Christian
Christian 2015-5-19
Hi there, although this thread is really old, I'm gonna give it a shot :-) I encountered the same problem and Matt's formula seems to solve it beautifully when regressing against only 1 independent variable. However, my x contains 4 factors. How would you go about calculating R-squared in that case? I tried the following, but it doesn't seem to work:
B_Rsqrd(1,j) = corr(Y,b(1)+b(2)*X(:,1)+b(3)*X(:,2)+b(4)*X(:,3)+b(5)*X(:,4))^2;
Can someone help me out here?
Any help is much appreciated!
Christian

类别

在 Help Center 和 File Exchange 中查找有关 Linear Regression 的更多信息

标签

Community Treasure Hunt

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

Start Hunting!

Translated by