3
$\begingroup$

I was came across different formulas for R squared on different articles.

R Squared = 1 - RSS/TSS

R Squared = ESS/TSS

RSS -Residual sum of squares. TSS - Total sum of squares. ESS - Explained sum of squares.

Can any one explain which one should be the correct one.

$\endgroup$
2
$\begingroup$

Both are correct. R squared tells you how many variance of the dependent variable is explained by your model. This can be written in different ways. It is like to say that the probability of being alive is 1 minus the probability of dying.

ESS=TSS-RSS

https://en.m.wikipedia.org/wiki/Coefficient_of_determination

[1]: https://i.stack.imgur.com/QlM6O.jpgenter image description here

|improve this answer|||||
$\endgroup$
1
$\begingroup$

Technical explanation There are many ways to construct regression models, and depending on the model some properties may behave differently and the two formulations reflect the behavior of test results. Neither is always applicable.

Regression is a powerful tool because so many things have a linear relationship. But it's also easy to mess up. I recently wrote about the basics of interpreting simple linear regression models and some of the details for beginners.

|improve this answer|||||
$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.